|
|
|
@@ -0,0 +1,231 @@
|
|
|
|
|
{"task_id": "easy-intent-00", "family": "intent", "split": "public", "group": null, "ts": 1790798638.2069888, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "track_order", "ordinal_ev": null, "probs": {"billing_question": 0.0037157811604703298, "cancel_order": 0.003078293568895903, "change_address": 0.001361767731259195, "report_damage": 0.0032776061174943907, "track_order": 0.9885665514218801}, "probs_as_returned": {"billing_question": 0.0037157811604703298, "cancel_order": 0.003078293568895903, "change_address": 0.001361767731259195, "report_damage": 0.0032776061174943907, "track_order": 0.9885665514218801}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.06874561496078968, "usage": {"input_tokens": 237, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "b2bad1dca36325921ed023838d3df5b006c364286d98f761f045d082ca8ee15e", "runtime": null}
|
|
|
|
|
{"task_id": "easy-intent-01", "family": "intent", "split": "public", "group": null, "ts": 1790798638.2699797, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "cancel_order", "ordinal_ev": null, "probs": {"billing_question": 0.008350062041863383, "cancel_order": 0.9827395556133772, "change_address": 0.002380980312875335, "report_damage": 0.003060149037375123, "track_order": 0.003469252994509084}, "probs_as_returned": {"billing_question": 0.008350062041863383, "cancel_order": 0.9827395556133772, "change_address": 0.002380980312875335, "report_damage": 0.003060149037375123, "track_order": 0.003469252994509084}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.055240098969079554, "usage": {"input_tokens": 237, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "f5ec8ef16d8c8b2c731836eec38b6d7a3fceca9fa461c4dfb550da255ea78a1a", "runtime": null}
|
|
|
|
|
{"task_id": "easy-intent-02", "family": "intent", "split": "public", "group": null, "ts": 1790798638.3310382, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "change_address", "ordinal_ev": null, "probs": {"billing_question": 0.006453941294493193, "cancel_order": 0.004160046017396561, "change_address": 0.976248827903928, "report_damage": 0.0053466891642593726, "track_order": 0.007790495619922923}, "probs_as_returned": {"billing_question": 0.006453941294493193, "cancel_order": 0.004160046017396561, "change_address": 0.976248827903928, "report_damage": 0.0053466891642593726, "track_order": 0.007790495619922923}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05404605797957629, "usage": {"input_tokens": 239, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "339197e295109120763738291721dda40ffa029641e32423e5f879a19352d6ad", "runtime": null}
|
|
|
|
|
{"task_id": "easy-intent-03", "family": "intent", "split": "public", "group": null, "ts": 1790798638.3929644, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "report_damage", "ordinal_ev": null, "probs": {"billing_question": 0.0032856469914429327, "cancel_order": 0.0024009737772375207, "change_address": 0.0014534960934417126, "report_damage": 0.9909917808872951, "track_order": 0.0018681022505827403}, "probs_as_returned": {"billing_question": 0.0032856469914429327, "cancel_order": 0.0024009737772375207, "change_address": 0.0014534960934417126, "report_damage": 0.9909917808872951, "track_order": 0.0018681022505827403}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05379386804997921, "usage": {"input_tokens": 228, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "95abc92944fc85cc275e375a3afac504e3d263296db623756c4773e011403718", "runtime": null}
|
|
|
|
|
{"task_id": "easy-intent-04", "family": "intent", "split": "public", "group": null, "ts": 1790798638.4550037, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "billing_question", "ordinal_ev": null, "probs": {"billing_question": 0.9920142822722872, "cancel_order": 0.005433032876037771, "change_address": 0.0007769531103232375, "report_damage": 0.0011320744243103107, "track_order": 0.000643657317041507}, "probs_as_returned": {"billing_question": 0.9920142822722872, "cancel_order": 0.005433032876037771, "change_address": 0.0007769531103232375, "report_damage": 0.0011320744243103107, "track_order": 0.000643657317041507}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05448066600365564, "usage": {"input_tokens": 233, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "52c5d0beb42112b3aa6f578c1d6b106060f1813dc99a1e29139f1fe41bd6f3b2", "runtime": null}
|
|
|
|
|
{"task_id": "easy-intent-05", "family": "intent", "split": "public", "group": null, "ts": 1790798638.5167017, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "track_order", "ordinal_ev": null, "probs": {"billing_question": 0.005069572552208189, "cancel_order": 0.003479294303948175, "change_address": 0.0023878717693975727, "report_damage": 0.003479294303948175, "track_order": 0.9855839670704978}, "probs_as_returned": {"billing_question": 0.005069572552208189, "cancel_order": 0.003479294303948175, "change_address": 0.0023878717693975727, "report_damage": 0.003479294303948175, "track_order": 0.9855839670704978}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05416978499852121, "usage": {"input_tokens": 232, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "094a2f61c0c2022061cb78d28ea3fa73d5c43054cb53f20a3a04c448a9e9346c", "runtime": null}
|
|
|
|
|
{"task_id": "easy-intent-06", "family": "intent", "split": "public", "group": null, "ts": 1790798638.5803332, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "set_alarm", "ordinal_ev": null, "probs": {"play_music": 0.006093371416719093, "send_message": 0.003927632182349683, "set_alarm": 0.9813860625238946, "turn_off_lights": 0.005722831872794024, "weather": 0.0028701020042427037}, "probs_as_returned": {"play_music": 0.006093371416719093, "send_message": 0.003927632182349683, "set_alarm": 0.9813860625238946, "turn_off_lights": 0.005722831872794024, "weather": 0.0028701020042427037}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05521256796782836, "usage": {"input_tokens": 225, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "31448e2bdac666215efe6868305ca5f96fcd940704f5267a217485a7fb2545a0", "runtime": null}
|
|
|
|
|
{"task_id": "easy-intent-07", "family": "intent", "split": "public", "group": null, "ts": 1790798638.6416538, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "play_music", "ordinal_ev": null, "probs": {"play_music": 0.9889646607601771, "send_message": 0.00653800507921397, "set_alarm": 0.0017509134460344028, "turn_off_lights": 0.0017509134460344028, "weather": 0.000995507268540069}, "probs_as_returned": {"play_music": 0.9889646607601771, "send_message": 0.00653800507921397, "set_alarm": 0.0017509134460344028, "turn_off_lights": 0.0017509134460344028, "weather": 0.000995507268540069}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.054108821030240506, "usage": {"input_tokens": 218, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "4d29de71e97c7d6326b53b05ce6e00980547d29d4976f085cd6fd7093f047069", "runtime": null}
|
|
|
|
|
{"task_id": "easy-intent-08", "family": "intent", "split": "public", "group": null, "ts": 1790798638.7050102, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "weather", "ordinal_ev": null, "probs": {"play_music": 0.0073499617445077865, "send_message": 0.00417892749053501, "set_alarm": 0.0030537350538425087, "turn_off_lights": 0.0047375981872448125, "weather": 0.9806797775238698}, "probs_as_returned": {"play_music": 0.0073499617445077865, "send_message": 0.00417892749053501, "set_alarm": 0.0030537350538425087, "turn_off_lights": 0.0047375981872448125, "weather": 0.9806797775238698}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05550681398017332, "usage": {"input_tokens": 220, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "9db04d50ad9a3171b0fcb54bf2c7c131d23e992bea5b8d553bfefa1d06342d95", "runtime": null}
|
|
|
|
|
{"task_id": "easy-intent-09", "family": "intent", "split": "public", "group": null, "ts": 1790798638.7670717, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "send_message", "ordinal_ev": null, "probs": {"play_music": 0.012056092798137684, "send_message": 0.9738121212463231, "set_alarm": 0.004418343519024835, "turn_off_lights": 0.004704420988497517, "weather": 0.005009021448016902}, "probs_as_returned": {"play_music": 0.012056092798137684, "send_message": 0.9738121212463231, "set_alarm": 0.004418343519024835, "turn_off_lights": 0.004704420988497517, "weather": 0.005009021448016902}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05443960300181061, "usage": {"input_tokens": 223, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "bc941120969be4d15c1fd2f766a678684fa7075f54742fe4da431887bc68a2ae", "runtime": null}
|
|
|
|
|
{"task_id": "easy-intent-10", "family": "intent", "split": "public", "group": null, "ts": 1790798638.8299856, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "turn_off_lights", "ordinal_ev": null, "probs": {"play_music": 0.0037055333570594024, "send_message": 0.0034801987605495434, "set_alarm": 0.0032685666377679874, "turn_off_lights": 0.9858401678875638, "weather": 0.0037055333570594024}, "probs_as_returned": {"play_music": 0.0037055333570594024, "send_message": 0.0034801987605495434, "set_alarm": 0.0032685666377679874, "turn_off_lights": 0.9858401678875638, "weather": 0.0037055333570594024}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05479409598046914, "usage": {"input_tokens": 221, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "c0891177bf11031403fa1cd801431582fb5a5351792d7238a07afe69fdaf01cb", "runtime": null}
|
|
|
|
|
{"task_id": "easy-intent-11", "family": "intent", "split": "public", "group": null, "ts": 1790798638.8927832, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "set_alarm", "ordinal_ev": null, "probs": {"play_music": 0.00611383130526039, "send_message": 0.0027046210473488227, "set_alarm": 0.9846812885886964, "turn_off_lights": 0.004756929120067906, "weather": 0.0017433299386264444}, "probs_as_returned": {"play_music": 0.00611383130526039, "send_message": 0.0027046210473488227, "set_alarm": 0.9846812885886964, "turn_off_lights": 0.004756929120067906, "weather": 0.0017433299386264444}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05431723297806457, "usage": {"input_tokens": 221, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "5893e54059caa3aaefe356a0ea119fe5b09c5c6429f79619af74e57ba87c77cb", "runtime": null}
|
|
|
|
|
{"task_id": "easy-fact-00", "family": "fact", "split": "public", "group": null, "ts": 1790798638.9548666, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "yes", "ordinal_ev": null, "probs": {"yes": 0.9710643566281367, "no": 0.028935643371863273}, "probs_as_returned": {"yes": 0.9710643566281367, "no": 0.028935643371863273}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05449540197150782, "usage": {"input_tokens": 199, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "9d77a1bfe21bd6b0c5b5081e779ed07219650f2e1ca3a8e255619dd8974acf28", "runtime": null}
|
|
|
|
|
{"task_id": "easy-fact-01", "family": "fact", "split": "public", "group": null, "ts": 1790798639.0168176, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "no", "ordinal_ev": null, "probs": {"yes": 0.010802420461426548, "no": 0.9891975795385735}, "probs_as_returned": {"yes": 0.010802420461426548, "no": 0.9891975795385735}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05475255200872198, "usage": {"input_tokens": 197, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "09a5a0dd37f8d58eb5f648369c33ba21e072ecd9a44263104214c43b360f42a3", "runtime": null}
|
|
|
|
|
{"task_id": "easy-fact-02", "family": "fact", "split": "public", "group": null, "ts": 1790798639.0787601, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "yes", "ordinal_ev": null, "probs": {"yes": 0.9743891388556707, "no": 0.02561086114432931}, "probs_as_returned": {"yes": 0.9743891388556707, "no": 0.02561086114432931}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05460676900111139, "usage": {"input_tokens": 205, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "988ca48f88da2813f950d9fed23d7b01c638d422c0b5d95b3ac50e2bd5043f37", "runtime": null}
|
|
|
|
|
{"task_id": "easy-fact-03", "family": "fact", "split": "public", "group": null, "ts": 1790798639.142439, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "no", "ordinal_ev": null, "probs": {"yes": 0.011493812770397228, "no": 0.9885061872296028}, "probs_as_returned": {"yes": 0.011493812770397228, "no": 0.9885061872296028}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05668640899239108, "usage": {"input_tokens": 208, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "30f9a68d5631dd944e483cb6f1d7414de2241e8caf3787ffd35edaf45a25435a", "runtime": null}
|
|
|
|
|
{"task_id": "easy-fact-04", "family": "fact", "split": "public", "group": null, "ts": 1790798639.2028663, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "yes", "ordinal_ev": null, "probs": {"yes": 0.9710643566281367, "no": 0.028935643371863273}, "probs_as_returned": {"yes": 0.9710643566281367, "no": 0.028935643371863273}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05368404695764184, "usage": {"input_tokens": 197, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "5b6676f30f9f6874f9685be2511cf015d9eb723c5110bb43d2d3bb4b5bb31f6a", "runtime": null}
|
|
|
|
|
{"task_id": "easy-fact-05", "family": "fact", "split": "public", "group": null, "ts": 1790798639.2654843, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "no", "ordinal_ev": null, "probs": {"yes": 0.07967467169628852, "no": 0.9203253283037115}, "probs_as_returned": {"yes": 0.07967467169628852, "no": 0.9203253283037115}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.055040310020558536, "usage": {"input_tokens": 198, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "33918d443efba82e8542244c22810dd0fece014fa3e287dca792acdb9fee346c", "runtime": null}
|
|
|
|
|
{"task_id": "easy-fact-06", "family": "fact", "split": "public", "group": null, "ts": 1790798639.325963, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "yes", "ordinal_ev": null, "probs": {"yes": 0.9608203271108413, "no": 0.03917967288915869}, "probs_as_returned": {"yes": 0.9608203271108413, "no": 0.03917967288915869}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05386464501498267, "usage": {"input_tokens": 218, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "9c083ac2b6fbcd8cdc0f924d27b8eff6a3d0aa4c2f70f5760ff3bcd28079d0d6", "runtime": null}
|
|
|
|
|
{"task_id": "easy-fact-07", "family": "fact", "split": "public", "group": null, "ts": 1790798639.3872962, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "no", "ordinal_ev": null, "probs": {"yes": 0.016659759016074603, "no": 0.9833402409839254}, "probs_as_returned": {"yes": 0.016659759016074603, "no": 0.9833402409839254}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05440297501627356, "usage": {"input_tokens": 193, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "409f4934c23150c498561bd298a1a77ccce38f31e75a51d474023077811e3e77", "runtime": null}
|
|
|
|
|
{"task_id": "easy-fact-08", "family": "fact", "split": "public", "group": null, "ts": 1790798639.4495173, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "yes", "ordinal_ev": null, "probs": {"yes": 0.9759090252955993, "no": 0.02409097470440069}, "probs_as_returned": {"yes": 0.9759090252955993, "no": 0.02409097470440069}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05487698898650706, "usage": {"input_tokens": 189, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "ab96100b1b6d1be3560b361043eea4dc7bca601fd6338799fd40b553834c04f0", "runtime": null}
|
|
|
|
|
{"task_id": "easy-fact-09", "family": "fact", "split": "public", "group": null, "ts": 1790798639.510759, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "no", "ordinal_ev": null, "probs": {"yes": 0.013841134222312299, "no": 0.9861588657776877}, "probs_as_returned": {"yes": 0.013841134222312299, "no": 0.9861588657776877}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05420191999292001, "usage": {"input_tokens": 189, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "78f53b41dcfbbfe3fedc9b392c29ed5e3c8ab9439e43164513965cc3dfd437f1", "runtime": null}
|
|
|
|
|
{"task_id": "easy-fact-10", "family": "fact", "split": "public", "group": null, "ts": 1790798639.5724316, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "yes", "ordinal_ev": null, "probs": {"yes": 0.9405016353866033, "no": 0.05949836461339675}, "probs_as_returned": {"yes": 0.9405016353866033, "no": 0.05949836461339675}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.054406058974564075, "usage": {"input_tokens": 197, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "66a931dd86d426049c6a30e3ffe033c5c344e9ad50393f2924f64d9d5da15ef3", "runtime": null}
|
|
|
|
|
{"task_id": "easy-fact-11", "family": "fact", "split": "public", "group": null, "ts": 1790798639.6346092, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "no", "ordinal_ev": null, "probs": {"yes": 0.012228909296002857, "no": 0.9877710907039972}, "probs_as_returned": {"yes": 0.012228909296002857, "no": 0.9877710907039972}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.054342168965376914, "usage": {"input_tokens": 198, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "da029965d99a4d271c97e598e35592c537d9079a0087b539ef7d17fe693f3d28", "runtime": null}
|
|
|
|
|
{"task_id": "easy-extraction-00", "family": "extraction", "split": "public", "group": null, "ts": 1790798639.6968741, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "paypal", "ordinal_ev": null, "probs": {"bank_transfer": 0.005387207125398065, "cash": 0.004462965891172113, "credit_card": 0.006502850175498755, "paypal": 0.9836469768079311}, "probs_as_returned": {"bank_transfer": 0.005387207125398065, "cash": 0.004462965891172113, "credit_card": 0.006502850175498755, "paypal": 0.9836469768079311}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05457222898257896, "usage": {"input_tokens": 191, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "e992ccf99cb3189f5f9528f1a2fdbd659d25cde63d98dba76bb3585d3aafca75", "runtime": null}
|
|
|
|
|
{"task_id": "easy-extraction-01", "family": "extraction", "split": "public", "group": null, "ts": 1790798639.7589421, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "cash", "ordinal_ev": null, "probs": {"bank_transfer": 0.005362202749492144, "cash": 0.9790814538511988, "credit_card": 0.011384226924270966, "paypal": 0.004172116475037995}, "probs_as_returned": {"bank_transfer": 0.005362202749492144, "cash": 0.9790814538511988, "credit_card": 0.011384226924270966, "paypal": 0.004172116475037995}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.054484873020555824, "usage": {"input_tokens": 193, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "a895c7a4148c765cd3943198aaa7c721dfea9be0000972216a13292ed3f4902c", "runtime": null}
|
|
|
|
|
{"task_id": "easy-extraction-02", "family": "extraction", "split": "public", "group": null, "ts": 1790798639.822403, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "bank_transfer", "ordinal_ev": null, "probs": {"bank_transfer": 0.9886611045091759, "cash": 0.006959188878070115, "credit_card": 0.002395327053946649, "paypal": 0.001984379558807392}, "probs_as_returned": {"bank_transfer": 0.9886611045091759, "cash": 0.006959188878070115, "credit_card": 0.002395327053946649, "paypal": 0.001984379558807392}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05552484397776425, "usage": {"input_tokens": 194, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "c29e3eddef0579c23fe23603b6c68fa1e69131aa96af64dda34e2d467fe7149e", "runtime": null}
|
|
|
|
|
{"task_id": "easy-extraction-03", "family": "extraction", "split": "public", "group": null, "ts": 1790798639.887054, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "high", "ordinal_ev": null, "probs": {"high": 0.9233443241587275, "low": 0.012959506894251118, "medium": 0.01217143488730339, "urgent": 0.051524734059717935}, "probs_as_returned": {"high": 0.9233443241587275, "low": 0.012959506894251118, "medium": 0.01217143488730339, "urgent": 0.051524734059717935}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05516892997547984, "usage": {"input_tokens": 196, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "69cbfce77aaaf5cb1c684a059544e25d1ec068e636a0748bed06b534bfb27db2", "runtime": null}
|
|
|
|
|
{"task_id": "easy-extraction-04", "family": "extraction", "split": "public", "group": null, "ts": 1790798639.9528973, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "low", "ordinal_ev": null, "probs": {"high": 0.012079556291950424, "low": 0.9757073270220792, "medium": 0.007786174264223241, "urgent": 0.004426942421747175}, "probs_as_returned": {"high": 0.012079556291950424, "low": 0.9757073270220792, "medium": 0.007786174264223241, "urgent": 0.004426942421747175}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05597657401813194, "usage": {"input_tokens": 194, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "b49f90c9a99cf0278aad9e85b74d5c55db3771fb76bf1bddc0863baea4095bfc", "runtime": null}
|
|
|
|
|
{"task_id": "easy-extraction-05", "family": "extraction", "split": "public", "group": null, "ts": 1790798640.016384, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "urgent", "ordinal_ev": null, "probs": {"high": 0.012123545380943897, "low": 0.004172879641756854, "medium": 0.004443063766191328, "urgent": 0.9792605112111079}, "probs_as_returned": {"high": 0.012123545380943897, "low": 0.004172879641756854, "medium": 0.004443063766191328, "urgent": 0.9792605112111079}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05470560601679608, "usage": {"input_tokens": 194, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "9a5e4c68608ae521d66a8bdd80fb2d6acd5084d4788847eb9e4856227726de80", "runtime": null}
|
|
|
|
|
{"task_id": "easy-extraction-06", "family": "extraction", "split": "public", "group": null, "ts": 1790798640.081975, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "M", "ordinal_ev": null, "probs": {"L": 0.011362559593985683, "M": 0.9772179520276576, "S": 0.006067491605402367, "XL": 0.005351996772954305}, "probs_as_returned": {"L": 0.011362559593985683, "M": 0.9772179520276576, "S": 0.006067491605402367, "XL": 0.005351996772954305}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05716023105196655, "usage": {"input_tokens": 187, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "8d1ef1e860db384aaa43ea78f1282508f0df0d512d12bbe477a51b13fc29ab2f", "runtime": null}
|
|
|
|
|
{"task_id": "easy-extraction-07", "family": "extraction", "split": "public", "group": null, "ts": 1790798640.143911, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "XL", "ordinal_ev": null, "probs": {"L": 0.0236463954766581, "M": 0.009227085930027284, "S": 0.009227085930027284, "XL": 0.9578994326632874}, "probs_as_returned": {"L": 0.0236463954766581, "M": 0.009227085930027284, "S": 0.009227085930027284, "XL": 0.9578994326632874}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05469108099350706, "usage": {"input_tokens": 184, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "ba3d13cc1432bf0412ca9da32a1fabe48aa5e20c2a0cdbbf7c08736f1460bd25", "runtime": null}
|
|
|
|
|
{"task_id": "easy-extraction-08", "family": "extraction", "split": "public", "group": null, "ts": 1790798640.2070944, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "thursday", "ordinal_ev": null, "probs": {"friday": 0.005378595700972278, "monday": 0.0030580785963976943, "thursday": 0.9820746521827389, "tuesday": 0.0047443367599455805, "wednesday": 0.0047443367599455805}, "probs_as_returned": {"friday": 0.005378595700972278, "monday": 0.0030580785963976943, "thursday": 0.9820746521827389, "tuesday": 0.0047443367599455805, "wednesday": 0.0047443367599455805}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.055218946014065295, "usage": {"input_tokens": 195, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "88ffdf64267e72ff035735371314a5846ff6c6ae8fe933f992c87cb712327f33", "runtime": null}
|
|
|
|
|
{"task_id": "easy-extraction-09", "family": "extraction", "split": "public", "group": null, "ts": 1790798640.2698197, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "monday", "ordinal_ev": null, "probs": {"friday": 0.006487826443252909, "monday": 0.9813744363156989, "thursday": 0.00223308577898157, "tuesday": 0.004181887565710403, "wednesday": 0.005722763896356328}, "probs_as_returned": {"friday": 0.006487826443252909, "monday": 0.9813744363156989, "thursday": 0.00223308577898157, "tuesday": 0.004181887565710403, "wednesday": 0.005722763896356328}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.054923444986343384, "usage": {"input_tokens": 197, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "41ce67df9fd35e24d5065d98990674fa9985408ab41092198c238a6fc116dada", "runtime": null}
|
|
|
|
|
{"task_id": "easy-extraction-10", "family": "extraction", "split": "public", "group": null, "ts": 1790798640.3319952, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "friday", "ordinal_ev": null, "probs": {"friday": 0.9843070496345583, "monday": 0.005390822043802262, "thursday": 0.005063004435363676, "tuesday": 0.0019756402868039927, "wednesday": 0.0032634835994717003}, "probs_as_returned": {"friday": 0.9843070496345583, "monday": 0.005390822043802262, "thursday": 0.005063004435363676, "tuesday": 0.0019756402868039927, "wednesday": 0.0032634835994717003}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.054691806028131396, "usage": {"input_tokens": 192, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "971219d1b4cb7e4accb6d4d86444b142ecbe967af212e1c179f5f8ce8c800fad", "runtime": null}
|
|
|
|
|
{"task_id": "easy-extraction-11", "family": "extraction", "split": "public", "group": null, "ts": 1790798640.3955486, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "credit_card", "ordinal_ev": null, "probs": {"bank_transfer": 0.00782696473030407, "cash": 0.004450134632367189, "credit_card": 0.9808189129742555, "paypal": 0.006903987663073161}, "probs_as_returned": {"bank_transfer": 0.00782696473030407, "cash": 0.004450134632367189, "credit_card": 0.9808189129742555, "paypal": 0.006903987663073161}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05494489404372871, "usage": {"input_tokens": 198, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "a78d26c31a5b4733e06d04738afcff3f55b004ce58b0d6486fa880ad9f9573bc", "runtime": null}
|
|
|
|
|
{"task_id": "easy-tool_selection-00", "family": "tool_selection", "split": "public", "group": null, "ts": 1790798640.4612741, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "get_weather", "ordinal_ev": null, "probs": {"convert_currency": 0.007829807987743406, "create_calendar_event": 0.0032530999253130594, "get_weather": 0.9811752060057245, "send_email": 0.0050468950765359955, "translate_text": 0.0026949910046831105}, "probs_as_returned": {"convert_currency": 0.007829807987743406, "create_calendar_event": 0.0032530999253130594, "get_weather": 0.9811752060057245, "send_email": 0.0050468950765359955, "translate_text": 0.0026949910046831105}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.056156586040742695, "usage": {"input_tokens": 227, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "ec6cf42cab5909c2b06a6e4ab650cdea08a85222c98e2e2ec46f77a3874e25f6", "runtime": null}
|
|
|
|
|
{"task_id": "easy-tool_selection-01", "family": "tool_selection", "split": "public", "group": null, "ts": 1790798640.5249567, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "send_email", "ordinal_ev": null, "probs": {"convert_currency": 0.004770803588408859, "create_calendar_event": 0.0034862463985914503, "get_weather": 0.001642093020855755, "send_email": 0.9875532959266949, "translate_text": 0.0025475610654490583}, "probs_as_returned": {"convert_currency": 0.004770803588408859, "create_calendar_event": 0.0034862463985914503, "get_weather": 0.001642093020855755, "send_email": 0.9875532959266949, "translate_text": 0.0025475610654490583}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.055144930025562644, "usage": {"input_tokens": 229, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "9407dd18cb63cabd0ed0d77f4239d2c74567c5e050e2a8bb687f573cfeddd4e9", "runtime": null}
|
|
|
|
|
{"task_id": "easy-tool_selection-02", "family": "tool_selection", "split": "public", "group": null, "ts": 1790798640.5879774, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "create_calendar_event", "ordinal_ev": null, "probs": {"convert_currency": 0.006516607444799637, "create_calendar_event": 0.9857279498146715, "get_weather": 0.001978492219286686, "send_email": 0.0030694545003598877, "translate_text": 0.002707496020882359}, "probs_as_returned": {"convert_currency": 0.006516607444799637, "create_calendar_event": 0.9857279498146715, "get_weather": 0.001978492219286686, "send_email": 0.0030694545003598877, "translate_text": 0.002707496020882359}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.054617764020804316, "usage": {"input_tokens": 232, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "85e8f13fb405c38c63fefd1eb82535a17d0aa7b624dbc5af3857bcbb836f4316", "runtime": null}
|
|
|
|
|
{"task_id": "easy-tool_selection-03", "family": "tool_selection", "split": "public", "group": null, "ts": 1790798640.6499195, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "convert_currency", "ordinal_ev": null, "probs": {"convert_currency": 0.9879132695583835, "create_calendar_event": 0.0050815538345912745, "get_weather": 0.0017490519673023376, "send_email": 0.0015427989590568122, "translate_text": 0.003713325680665897}, "probs_as_returned": {"convert_currency": 0.9879132695583835, "create_calendar_event": 0.0050815538345912745, "get_weather": 0.0017490519673023376, "send_email": 0.0015427989590568122, "translate_text": 0.003713325680665897}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05402825499186292, "usage": {"input_tokens": 229, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "c3ebbd9f2b0d7f9b70f40ebdcc1d8ceffc973e29571e20f6b187f6af669267e4", "runtime": null}
|
|
|
|
|
{"task_id": "easy-tool_selection-04", "family": "tool_selection", "split": "public", "group": null, "ts": 1790798640.7120109, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "translate_text", "ordinal_ev": null, "probs": {"convert_currency": 0.0065024668896828735, "create_calendar_event": 0.004462702891725051, "get_weather": 0.002383038386749453, "send_email": 0.0030627940173430794, "translate_text": 0.9835889978144995}, "probs_as_returned": {"convert_currency": 0.0065024668896828735, "create_calendar_event": 0.004462702891725051, "get_weather": 0.002383038386749453, "send_email": 0.0030627940173430794, "translate_text": 0.9835889978144995}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05447351798648015, "usage": {"input_tokens": 226, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "86ad0f11a848371627180b8512ca8bedb1e9f9555b8ccd9dff69ea38538db154", "runtime": null}
|
|
|
|
|
{"task_id": "easy-tool_selection-05", "family": "tool_selection", "split": "public", "group": null, "ts": 1790798640.7727077, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "create_calendar_event", "ordinal_ev": null, "probs": {"convert_currency": 0.007354093936894176, "create_calendar_event": 0.9812311228123023, "get_weather": 0.0022327596869927153, "send_email": 0.006486878942590166, "translate_text": 0.002695144621220672}, "probs_as_returned": {"convert_currency": 0.007354093936894176, "create_calendar_event": 0.9812311228123023, "get_weather": 0.0022327596869927153, "send_email": 0.006486878942590166, "translate_text": 0.002695144621220672}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05395827104803175, "usage": {"input_tokens": 232, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "ddedecbac6acccd9447a8eba538b1f6c8a0d7b356cb41ee4f91cba89cd16c23f", "runtime": null}
|
|
|
|
|
{"task_id": "easy-tool_selection-06", "family": "tool_selection", "split": "public", "group": null, "ts": 1790798640.8339195, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "search_flights", "ordinal_ev": null, "probs": {"book_restaurant": 0.002723028128906097, "call_taxi": 0.0022558595435807336, "get_stock_price": 0.0019898423713477923, "search_flights": 0.9913828092209783, "set_reminder": 0.0016484607351869884}, "probs_as_returned": {"book_restaurant": 0.002723028128906097, "call_taxi": 0.0022558595435807336, "get_stock_price": 0.0019898423713477923, "search_flights": 0.9913828092209783, "set_reminder": 0.0016484607351869884}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05415012000594288, "usage": {"input_tokens": 236, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "725ebcf977de66dcb33698f213f6adc8372ad26774c2541d3557edad71b90d70", "runtime": null}
|
|
|
|
|
{"task_id": "easy-tool_selection-07", "family": "tool_selection", "split": "public", "group": null, "ts": 1790798640.8953264, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "book_restaurant", "ordinal_ev": null, "probs": {"book_restaurant": 0.9875027503742834, "call_taxi": 0.005758500527357331, "get_stock_price": 0.0010583971646233432, "search_flights": 0.0011998917646541929, "set_reminder": 0.004480460169081839}, "probs_as_returned": {"book_restaurant": 0.9875027503742834, "call_taxi": 0.005758500527357331, "get_stock_price": 0.0010583971646233432, "search_flights": 0.0011998917646541929, "set_reminder": 0.004480460169081839}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05422466801246628, "usage": {"input_tokens": 236, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "a7573351cdaf14a93adc2836d77815f873edce9f83161815382e3203ad3037f7", "runtime": null}
|
|
|
|
|
{"task_id": "easy-tool_selection-08", "family": "tool_selection", "split": "public", "group": null, "ts": 1790798640.9579682, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "set_reminder", "ordinal_ev": null, "probs": {"book_restaurant": 0.0027204340659280554, "call_taxi": 0.0022537104865137892, "get_stock_price": 0.0018670590411967879, "search_flights": 0.0027204340659280554, "set_reminder": 0.9904383623404333}, "probs_as_returned": {"book_restaurant": 0.0027204340659280554, "call_taxi": 0.0022537104865137892, "get_stock_price": 0.0018670590411967879, "search_flights": 0.0027204340659280554, "set_reminder": 0.9904383623404333}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05488467600662261, "usage": {"input_tokens": 235, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "393a7c4473446a5ace45b1f82c606b24bc010e665eef5630aec2278bb920cbf9", "runtime": null}
|
|
|
|
|
{"task_id": "easy-tool_selection-09", "family": "tool_selection", "split": "public", "group": null, "ts": 1790798641.0200438, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "get_stock_price", "ordinal_ev": null, "probs": {"book_restaurant": 0.006098491673709373, "call_taxi": 0.0030585022990139332, "get_stock_price": 0.98221073526815, "search_flights": 0.006098491673709373, "set_reminder": 0.0025337790854174126}, "probs_as_returned": {"book_restaurant": 0.006098491673709373, "call_taxi": 0.0030585022990139332, "get_stock_price": 0.98221073526815, "search_flights": 0.006098491673709373, "set_reminder": 0.0025337790854174126}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.053883728047367185, "usage": {"input_tokens": 231, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "894e1751e54692f3a26a11d692bf7d6d4c640abf46fc4b104b34d01202b4dae6", "runtime": null}
|
|
|
|
|
{"task_id": "easy-tool_selection-10", "family": "tool_selection", "split": "public", "group": null, "ts": 1790798641.0817819, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "call_taxi", "ordinal_ev": null, "probs": {"book_restaurant": 0.008868475619137011, "call_taxi": 0.9802820079262876, "get_stock_price": 0.002230600011225041, "search_flights": 0.0053687778295083005, "set_reminder": 0.0032501386138420975}, "probs_as_returned": {"book_restaurant": 0.008868475619137011, "call_taxi": 0.9802820079262876, "get_stock_price": 0.002230600011225041, "search_flights": 0.0053687778295083005, "set_reminder": 0.0032501386138420975}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.054214395000599325, "usage": {"input_tokens": 232, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "baedb703f80339715aa50eeb87c6c0ab771811495856578a00fcef10e8e1d5e5", "runtime": null}
|
|
|
|
|
{"task_id": "easy-tool_selection-11", "family": "tool_selection", "split": "public", "group": null, "ts": 1790798641.1430955, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "set_reminder", "ordinal_ev": null, "probs": {"book_restaurant": 0.0024029836241437775, "call_taxi": 0.0018696659764764975, "get_stock_price": 0.0016491898330211032, "search_flights": 0.002256857361858334, "set_reminder": 0.9918213032045002}, "probs_as_returned": {"book_restaurant": 0.0024029836241437775, "call_taxi": 0.0018696659764764975, "get_stock_price": 0.0016491898330211032, "search_flights": 0.002256857361858334, "set_reminder": 0.9918213032045002}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05420462001347914, "usage": {"input_tokens": 235, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "2a6d4b29ebe7a1259dcab75d70baef81981673a73b9b127d850cb2063f4d5a0e", "runtime": null}
|
|
|
|
|
{"task_id": "original-policy-01-0", "family": "policy", "split": "public", "group": "original-policy-01", "ts": 1790798641.2058475, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "no", "ordinal_ev": null, "probs": {"yes": 0.022659190258890113, "no": 0.9773408097411099}, "probs_as_returned": {"yes": 0.022659190258890113, "no": 0.9773408097411099}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05488112603779882, "usage": {"input_tokens": 219, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "c5d2db129c77aec322f0bd6a81ac46c02d175d89ea46a4fae445eb6e6fc51ccc", "runtime": null}
|
|
|
|
|
{"task_id": "original-policy-01-1", "family": "policy", "split": "public", "group": "original-policy-01", "ts": 1790798641.2676349, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "no", "ordinal_ev": null, "probs": {"yes": 0.005797568831524007, "no": 0.994202431168476}, "probs_as_returned": {"yes": 0.005797568831524007, "no": 0.994202431168476}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05413453502114862, "usage": {"input_tokens": 221, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "be85e3385ed14b6eb430262a288c518b2394627a43f28a6ce893f06117c7bae9", "runtime": null}
|
|
|
|
|
{"task_id": "original-policy-02-0", "family": "policy", "split": "public", "group": "original-policy-02", "ts": 1790798641.329739, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "yes", "ordinal_ev": null, "probs": {"yes": 0.9652800911770798, "no": 0.0347199088229202}, "probs_as_returned": {"yes": 0.9652800911770798, "no": 0.0347199088229202}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05379870202159509, "usage": {"input_tokens": 208, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "34cf3ab2e98a7e3a9abc9c48616e82f8ae10c2d133231f31feb53c146301810c", "runtime": null}
|
|
|
|
|
{"task_id": "original-policy-02-1", "family": "policy", "split": "public", "group": "original-policy-02", "ts": 1790798641.3928397, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "yes", "ordinal_ev": null, "probs": {"yes": 0.91062577829021, "no": 0.08937422170979004}, "probs_as_returned": {"yes": 0.91062577829021, "no": 0.08937422170979004}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05498998297844082, "usage": {"input_tokens": 206, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "99c7a9cc42d9a278d4e4cc5dd6a40816f83e90c582df7a711da720e16263529b", "runtime": null}
|
|
|
|
|
{"task_id": "original-policy-03-0", "family": "policy", "split": "public", "group": "original-policy-03", "ts": 1790798641.4547215, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "yes", "ordinal_ev": null, "probs": {"yes": 0.8879876242264044, "no": 0.11201237577359557}, "probs_as_returned": {"yes": 0.8879876242264044, "no": 0.11201237577359557}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05470967502333224, "usage": {"input_tokens": 210, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "8ba3ef52048dd3adde4f594c2fe5549f187c19b5b8f1b3d20d9d25dc3419e1cd", "runtime": null}
|
|
|
|
|
{"task_id": "original-policy-03-1", "family": "policy", "split": "public", "group": "original-policy-03", "ts": 1790798641.5188625, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "yes", "ordinal_ev": null, "probs": {"yes": 0.7557061813028185, "no": 0.24429381869718148}, "probs_as_returned": {"yes": 0.7557061813028185, "no": 0.24429381869718148}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05510559998219833, "usage": {"input_tokens": 209, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "21c823210673ffecb9bece216377aa5759bacd24655d600f8f048ce7d79db37a", "runtime": null}
|
|
|
|
|
{"task_id": "original-policy-04-0", "family": "policy", "split": "public", "group": "original-policy-04", "ts": 1790798641.5847313, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "no", "ordinal_ev": null, "probs": {"yes": 0.09461348765523125, "no": 0.9053865123447687}, "probs_as_returned": {"yes": 0.09461348765523125, "no": 0.9053865123447687}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.056224071013275534, "usage": {"input_tokens": 216, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "f6258124545a57982a7024524ed22dfcf6926ee0c32191a172b7aa6d79a9133b", "runtime": null}
|
|
|
|
|
{"task_id": "original-policy-04-1", "family": "policy", "split": "public", "group": "original-policy-04", "ts": 1790798641.647213, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "no", "ordinal_ev": null, "probs": {"yes": 0.012228909296002857, "no": 0.9877710907039972}, "probs_as_returned": {"yes": 0.012228909296002857, "no": 0.9877710907039972}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.054383432026952505, "usage": {"input_tokens": 212, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "f14bfe20af7b9b22440d7c0a919f8cb1de73843b45b74cdea79e06ae29b782fa", "runtime": null}
|
|
|
|
|
{"task_id": "original-policy-05-0", "family": "policy", "split": "public", "group": "original-policy-05", "ts": 1790798641.7104824, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "no", "ordinal_ev": null, "probs": {"yes": 0.03917967288915878, "no": 0.9608203271108412}, "probs_as_returned": {"yes": 0.03917967288915878, "no": 0.9608203271108412}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05544484598794952, "usage": {"input_tokens": 220, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "106b31fdbb2c33a9e5a8e73c05faf1dc821f7db251432377d3a60116ba1c621a", "runtime": null}
|
|
|
|
|
{"task_id": "original-policy-05-1", "family": "policy", "split": "public", "group": "original-policy-05", "ts": 1790798641.7729447, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "no", "ordinal_ev": null, "probs": {"yes": 0.04979902705524531, "no": 0.9502009729447547}, "probs_as_returned": {"yes": 0.04979902705524531, "no": 0.9502009729447547}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.054668257012963295, "usage": {"input_tokens": 212, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "79dba0f8768b16d65fbac0a24522600f435d824b01c3bbacbd7d47faf444674b", "runtime": null}
|
|
|
|
|
{"task_id": "original-policy-06-0", "family": "policy", "split": "public", "group": "original-policy-06", "ts": 1790798641.835886, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "yes", "ordinal_ev": null, "probs": {"yes": 0.91062577829021, "no": 0.08937422170979004}, "probs_as_returned": {"yes": 0.91062577829021, "no": 0.08937422170979004}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.054601289972197264, "usage": {"input_tokens": 222, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "6e22f50201481749378f74bb1fc0f8b6858cac69099359afdde3bb9b53dc7c82", "runtime": null}
|
|
|
|
|
{"task_id": "original-policy-06-1", "family": "policy", "split": "public", "group": "original-policy-06", "ts": 1790798641.8992229, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "yes", "ordinal_ev": null, "probs": {"yes": 0.8604937671763584, "no": 0.1395062328236416}, "probs_as_returned": {"yes": 0.8604937671763584, "no": 0.1395062328236416}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05437642498873174, "usage": {"input_tokens": 211, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "88c95b71e89e320820140740f77ed08769fea884253d976f1c740cdb80501293", "runtime": null}
|
|
|
|
|
{"task_id": "original-intent-01-0", "family": "intent", "split": "public", "group": "original-intent-01", "ts": 1790798641.9616427, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "refund", "ordinal_ev": null, "probs": {"cancel": 0.019858206552561444, "change_address": 0.007277679357392087, "other": 0.11503962460331064, "refund": 0.8565281796860903, "status": 0.0012963098006456009}, "probs_as_returned": {"cancel": 0.019858206552561444, "change_address": 0.007277679357392087, "other": 0.11503962460331064, "refund": 0.8565281796860903, "status": 0.0012963098006456009}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.0541904479614459, "usage": {"input_tokens": 216, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "cb899f4257cf1f9e63841696d2cd05136fbb0ecdea3598bcb92d891239c56cbc", "runtime": null}
|
|
|
|
|
{"task_id": "original-intent-01-1", "family": "intent", "split": "public", "group": "original-intent-01", "ts": 1790798642.0233958, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "refund", "ordinal_ev": null, "probs": {"cancel": 0.013157397907281692, "change_address": 0.010900086144070705, "other": 0.19533400388242703, "refund": 0.7766138243051219, "status": 0.003994687761098555}, "probs_as_returned": {"cancel": 0.013157397907281692, "change_address": 0.010900086144070705, "other": 0.19533400388242703, "refund": 0.7766138243051219, "status": 0.003994687761098555}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05380670097656548, "usage": {"input_tokens": 218, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "21bbf295e0fbbf123cc97f4f841478d1aaeecaadebdb3a303b6a598fbb8553ee", "runtime": null}
|
|
|
|
|
{"task_id": "original-intent-02-0", "family": "intent", "split": "public", "group": "original-intent-02", "ts": 1790798642.0865393, "status": "ok", "ok": true, "valid": true, "correct": false, "predicted": "other", "ordinal_ev": null, "probs": {"cancel": 0.011108283739639322, "change_address": 0.017233512714200254, "other": 0.4791247461286767, "refund": 0.013408711288806937, "status": 0.4791247461286767}, "probs_as_returned": {"cancel": 0.011108283739639322, "change_address": 0.017233512714200254, "other": 0.4791247461286767, "refund": 0.013408711288806937, "status": 0.4791247461286767}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05440216202987358, "usage": {"input_tokens": 218, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "a4f0a0cf2c0b535996a79f22b29d3072a9aa61d2469af2f53855721161b96180", "runtime": null}
|
|
|
|
|
{"task_id": "original-intent-02-1", "family": "intent", "split": "public", "group": "original-intent-02", "ts": 1790798642.1485484, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "status", "ordinal_ev": null, "probs": {"cancel": 0.002321175467540561, "change_address": 0.0031764458100722866, "other": 0.0323645156724377, "refund": 0.004082518984442435, "status": 0.958055344065507}, "probs_as_returned": {"cancel": 0.002321175467540561, "change_address": 0.0031764458100722866, "other": 0.0323645156724377, "refund": 0.004082518984442435, "status": 0.958055344065507}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.0542256300104782, "usage": {"input_tokens": 217, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "d4249e62a13df9b65b7eedc17e2bf7f4189a14757f4c9423c376b2c54d0ad9a7", "runtime": null}
|
|
|
|
|
{"task_id": "original-intent-03-0", "family": "intent", "split": "public", "group": "original-intent-03", "ts": 1790798642.2099388, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "change_address", "ordinal_ev": null, "probs": {"cancel": 0.009915815183017014, "change_address": 0.9080094929418733, "other": 0.04469398562198547, "refund": 0.011969292639071262, "status": 0.02541141361405287}, "probs_as_returned": {"cancel": 0.009915815183017014, "change_address": 0.9080094929418733, "other": 0.04469398562198547, "refund": 0.011969292639071262, "status": 0.02541141361405287}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05372664099559188, "usage": {"input_tokens": 218, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "a3c64b3af9a284e90663fcf4dfa5fac4f097495d56107a18583df2a93f3f5900", "runtime": null}
|
|
|
|
|
{"task_id": "original-intent-03-1", "family": "intent", "split": "public", "group": "original-intent-03", "ts": 1790798642.271487, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "change_address", "ordinal_ev": null, "probs": {"cancel": 0.006265845660924066, "change_address": 0.947796734818206, "other": 0.03409105347210196, "refund": 0.008053162589058565, "status": 0.0037932034597093207}, "probs_as_returned": {"cancel": 0.006265845660924066, "change_address": 0.947796734818206, "other": 0.03409105347210196, "refund": 0.008053162589058565, "status": 0.0037932034597093207}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05377371399663389, "usage": {"input_tokens": 217, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "509d65dafbfb073b6994b65688307c209f96a23f5bab9b0d7f94cbcbd70bbe6d", "runtime": null}
|
|
|
|
|
{"task_id": "original-intent-04-0", "family": "intent", "split": "public", "group": "original-intent-04", "ts": 1790798642.33453, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "cancel", "ordinal_ev": null, "probs": {"cancel": 0.9378732275183023, "change_address": 0.004530802608425531, "other": 0.05233548212728289, "refund": 0.0042552831109369605, "status": 0.0010052046350524108}, "probs_as_returned": {"cancel": 0.9378732275183023, "change_address": 0.004530802608425531, "other": 0.05233548212728289, "refund": 0.0042552831109369605, "status": 0.0010052046350524108}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05451766197802499, "usage": {"input_tokens": 222, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "f51941a2eec2c0a6fef0f7fcf25f4e74feea5e0f88197a169c123a5f9c3d4492", "runtime": null}
|
|
|
|
|
{"task_id": "original-intent-04-1", "family": "intent", "split": "public", "group": "original-intent-04", "ts": 1790798642.3994598, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "cancel", "ordinal_ev": null, "probs": {"cancel": 0.947910801764849, "change_address": 0.004300825146805656, "other": 0.0438207144703226, "refund": 0.0029516958001635546, "status": 0.0010159628178592127}, "probs_as_returned": {"cancel": 0.947910801764849, "change_address": 0.004300825146805656, "other": 0.0438207144703226, "refund": 0.0029516958001635546, "status": 0.0010159628178592127}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.055575751001015306, "usage": {"input_tokens": 217, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "2ae2294d95dc81a5703d2b4229cfd098aa508b21a9f5d67251a7ba679350c077", "runtime": null}
|
|
|
|
|
{"task_id": "original-intent-05-0", "family": "intent", "split": "public", "group": "original-intent-05", "ts": 1790798642.4645169, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "other", "ordinal_ev": null, "probs": {"cancel": 0.007151922435870813, "change_address": 0.004066329316103547, "other": 0.697318944283325, "refund": 0.2897195038147706, "status": 0.0017433001499300139}, "probs_as_returned": {"cancel": 0.007151922435870813, "change_address": 0.004066329316103547, "other": 0.697318944283325, "refund": 0.2897195038147706, "status": 0.0017433001499300139}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.055316869053058326, "usage": {"input_tokens": 217, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "ab4fb635a66fadafe4bb26c0f477770669e02dd8b545af5918f698e071bda170", "runtime": null}
|
|
|
|
|
{"task_id": "original-intent-05-1", "family": "intent", "split": "public", "group": "original-intent-05", "ts": 1790798642.5295286, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "other", "ordinal_ev": null, "probs": {"cancel": 0.008842063949217063, "change_address": 0.00367366817047693, "other": 0.8621092581823092, "refund": 0.1232862922745069, "status": 0.0020887174234899913}, "probs_as_returned": {"cancel": 0.008842063949217063, "change_address": 0.00367366817047693, "other": 0.8621092581823092, "refund": 0.1232862922745069, "status": 0.0020887174234899913}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05528204201254994, "usage": {"input_tokens": 216, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "881258bef887b55b760b76fd760c1951e6f6c73a355860c737bb199ae6d8a604", "runtime": null}
|
|
|
|
|
{"task_id": "original-intent-06-0", "family": "intent", "split": "public", "group": "original-intent-06", "ts": 1790798642.5936453, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "status", "ordinal_ev": null, "probs": {"cancel": 0.04041415591597284, "change_address": 0.015770051641193803, "other": 0.2065130791599608, "refund": 0.013064506583094595, "status": 0.7242382066997779}, "probs_as_returned": {"cancel": 0.04041415591597284, "change_address": 0.015770051641193803, "other": 0.2065130791599608, "refund": 0.013064506583094595, "status": 0.7242382066997779}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05478964000940323, "usage": {"input_tokens": 214, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "f7a257d6b1623d74d9ec2c74ddd9e11868c5d87f4f5738c23e362d3186bb6f7e", "runtime": null}
|
|
|
|
|
{"task_id": "original-intent-06-1", "family": "intent", "split": "public", "group": "original-intent-06", "ts": 1790798642.6560948, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "status", "ordinal_ev": null, "probs": {"cancel": 0.010751220386095738, "change_address": 0.0078564127691029, "other": 0.10288184565711354, "refund": 0.010097435369874964, "status": 0.868413085817813}, "probs_as_returned": {"cancel": 0.010751220386095738, "change_address": 0.0078564127691029, "other": 0.10288184565711354, "refund": 0.010097435369874964, "status": 0.868413085817813}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05436096602352336, "usage": {"input_tokens": 219, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "480d5d42322a8381e8920a1263384baaa42c3e84dd58fc51557e744afbed9819", "runtime": null}
|
|
|
|
|
{"task_id": "original-ordinal-01-0", "family": "ordinal", "split": "public", "group": "original-ordinal-01", "ts": 1790798642.7171109, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "0", "ordinal_ev": 0.07628057138193826, "probs": {"0": 0.9336912617650633, "1": 0.05906752177300131, "2": 0.004510599776869139, "3": 0.0027306166850662277}, "probs_as_returned": {"0": 0.9336912617650633, "1": 0.05906752177300131, "2": 0.004510599776869139, "3": 0.0027306166850662277}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05400407797424123, "usage": {"input_tokens": 226, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "dac16e7f99d84ec570cf681c6f926893c23d66e4a2f49b455da0eb6ef7e5d01d", "runtime": null}
|
|
|
|
|
{"task_id": "original-ordinal-01-1", "family": "ordinal", "split": "public", "group": "original-ordinal-01", "ts": 1790798642.7785795, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "0", "ordinal_ev": 0.043562903333643106, "probs": {"0": 0.9617730521586384, "1": 0.03459376436924552, "2": 0.001930411451950494, "3": 0.0017027720201655324}, "probs_as_returned": {"0": 0.9617730521586384, "1": 0.03459376436924552, "2": 0.001930411451950494, "3": 0.0017027720201655324}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05383112502750009, "usage": {"input_tokens": 228, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "9a88e3a0012dec608e8a646d1dc96214f444b6409c17d6f75b6f2b756f5768b5", "runtime": null}
|
|
|
|
|
{"task_id": "original-ordinal-02-0", "family": "ordinal", "split": "public", "group": "original-ordinal-02", "ts": 1790798642.842795, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "1", "ordinal_ev": 0.9606073357096381, "probs": {"0": 0.06552783210496539, "1": 0.9136649245071803, "2": 0.015479318961105435, "3": 0.005327924426748972}, "probs_as_returned": {"0": 0.06552783210496539, "1": 0.9136649245071803, "2": 0.015479318961105435, "3": 0.005327924426748972}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.054606880992650986, "usage": {"input_tokens": 230, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "a998bb0eef538be56641b747f8a1101e86282ebe33ae43e8bad8ef573bc1a1e7", "runtime": null}
|
|
|
|
|
{"task_id": "original-ordinal-02-1", "family": "ordinal", "split": "public", "group": "original-ordinal-02", "ts": 1790798642.90627, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "1", "ordinal_ev": 0.9734045635133284, "probs": {"0": 0.03881697376711625, "1": 0.9519256866551472, "2": 0.006293141875028083, "3": 0.0029641977027083286}, "probs_as_returned": {"0": 0.03881697376711625, "1": 0.9519256866551472, "2": 0.006293141875028083, "3": 0.0029641977027083286}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.054924144002143294, "usage": {"input_tokens": 231, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "77dd5c790d7d4af46a564d0fcbf524f99cab0daeefdd733ccfa6e44d2514a03b", "runtime": null}
|
|
|
|
|
{"task_id": "original-ordinal-03-0", "family": "ordinal", "split": "public", "group": "original-ordinal-03", "ts": 1790798642.9688454, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "2", "ordinal_ev": 1.9918667458343595, "probs": {"0": 0.0060159904313022965, "1": 0.01058101655212649, "2": 0.9689232497674803, "3": 0.014479743249090765}, "probs_as_returned": {"0": 0.0060159904313022965, "1": 0.01058101655212649, "2": 0.9689232497674803, "3": 0.014479743249090765}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05385160900186747, "usage": {"input_tokens": 227, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "7b9a840ee0fef8f878e47af168a488159e01bf1dbd9c8981f9012089dfd2ab4d", "runtime": null}
|
|
|
|
|
{"task_id": "original-ordinal-03-1", "family": "ordinal", "split": "public", "group": "original-ordinal-03", "ts": 1790798643.0309207, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "2", "ordinal_ev": 2.00299542852447, "probs": {"0": 0.006773356163561288, "1": 0.007211914883152434, "2": 0.9622606732185414, "3": 0.023754055734744896}, "probs_as_returned": {"0": 0.006773356163561288, "1": 0.007211914883152434, "2": 0.9622606732185414, "3": 0.023754055734744896}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05395707598654553, "usage": {"input_tokens": 230, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "65f9074dcc620f995d41d4d94e1ad67860d61d1614e5ef4230be7a810d2b3d40", "runtime": null}
|
|
|
|
|
{"task_id": "original-ordinal-04-0", "family": "ordinal", "split": "public", "group": "original-ordinal-04", "ts": 1790798643.09286, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "3", "ordinal_ev": 2.9704331614645687, "probs": {"0": 0.004185713097107498, "1": 0.0034676031589811955, "2": 0.010074492926146724, "3": 0.9822721908177647}, "probs_as_returned": {"0": 0.004185713097107498, "1": 0.0034676031589811955, "2": 0.010074492926146724, "3": 0.9822721908177647}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05444974801503122, "usage": {"input_tokens": 230, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "7507a36c9101550ba86ad5062ce9ee41becf050ba7b9ba2c0d46e7c584adf741", "runtime": null}
|
|
|
|
|
{"task_id": "original-ordinal-04-1", "family": "ordinal", "split": "public", "group": "original-ordinal-04", "ts": 1790798643.1529746, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "3", "ordinal_ev": 2.967596710904972, "probs": {"0": 0.003917633194691461, "1": 0.003455654971049581, "2": 0.013739079568854744, "3": 0.9788876322654043}, "probs_as_returned": {"0": 0.003917633194691461, "1": 0.003455654971049581, "2": 0.013739079568854744, "3": 0.9788876322654043}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05312085401965305, "usage": {"input_tokens": 229, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "1c830a3f071f00319f11f41367656fc0ead0ace24fbcabe22eac191f2717a492", "runtime": null}
|
|
|
|
|
{"task_id": "original-ordinal-05-0", "family": "ordinal", "split": "public", "group": "original-ordinal-05", "ts": 1790798643.2149265, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "0", "ordinal_ev": 0.2291006823712572, "probs": {"0": 0.8500853530913438, "1": 0.08343242245188087, "2": 0.053778413450949664, "3": 0.012703811005825663}, "probs_as_returned": {"0": 0.8500853530913438, "1": 0.08343242245188087, "2": 0.053778413450949664, "3": 0.012703811005825663}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05434955202508718, "usage": {"input_tokens": 232, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "9a0963de3978ceac5bbf0b718bc1837d8c31c87eb0bb1b244f44d4e8b05fede7", "runtime": null}
|
|
|
|
|
{"task_id": "original-ordinal-05-1", "family": "ordinal", "split": "public", "group": "original-ordinal-05", "ts": 1790798643.2790198, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "0", "ordinal_ev": 0.12180446059244274, "probs": {"0": 0.9151321240993054, "1": 0.054372909340145624, "2": 0.024053348429349676, "3": 0.006441618131199253}, "probs_as_returned": {"0": 0.9151321240993054, "1": 0.054372909340145624, "2": 0.024053348429349676, "3": 0.006441618131199253}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05485840898472816, "usage": {"input_tokens": 232, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "f27509100029d1fd684b6aa5ec5642d1094f36b21c4ab0aa433d3b1820d8bd74", "runtime": null}
|
|
|
|
|
{"task_id": "original-ordinal-06-0", "family": "ordinal", "split": "public", "group": "original-ordinal-06", "ts": 1790798643.345078, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "2", "ordinal_ev": 1.9749699592964916, "probs": {"0": 0.006417617571413263, "1": 0.017511402806940014, "2": 0.9707543823753891, "3": 0.005316597246257736}, "probs_as_returned": {"0": 0.006417617571413263, "1": 0.017511402806940014, "2": 0.9707543823753891, "3": 0.005316597246257736}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05462758400244638, "usage": {"input_tokens": 233, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "066b1848ddfa640217c1995b8e898064f881c53e1927188c2ea16f9377b79340", "runtime": null}
|
|
|
|
|
{"task_id": "original-ordinal-06-1", "family": "ordinal", "split": "public", "group": "original-ordinal-06", "ts": 1790798643.4088457, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "2", "ordinal_ev": 1.9972653111993102, "probs": {"0": 0.002390359574020004, "1": 0.004476413325753633, "2": 0.9866107834271227, "3": 0.006522443673103714}, "probs_as_returned": {"0": 0.002390359574020004, "1": 0.004476413325753633, "2": 0.9866107834271227, "3": 0.006522443673103714}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05495850398438051, "usage": {"input_tokens": 240, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "86f5d38ebe5ccf4d3f9881b2e1dacf191ff1050bbb756b76926b9c031e16d312", "runtime": null}
|
|
|
|
|
{"task_id": "original-extraction-01-0", "family": "extraction", "split": "public", "group": "original-extraction-01", "ts": 1790798643.46985, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "pickup", "ordinal_ev": null, "probs": {"courier": 0.038581401175833197, "pickup": 0.9461486456144061, "post": 0.003556342540584308, "unknown": 0.011713610669176297}, "probs_as_returned": {"courier": 0.038581401175833197, "pickup": 0.9461486456144061, "post": 0.003556342540584308, "unknown": 0.011713610669176297}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05432673799805343, "usage": {"input_tokens": 204, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "b3ed70dc5eddd1423172e9de5b41e339d8163ff393d97b3a44eacb8d51a39257", "runtime": null}
|
|
|
|
|
{"task_id": "original-extraction-01-1", "family": "extraction", "split": "public", "group": "original-extraction-01", "ts": 1790798643.5308588, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "pickup", "ordinal_ev": null, "probs": {"courier": 0.02334986205840487, "pickup": 0.9458870455791862, "post": 0.004291643013286111, "unknown": 0.026471449349122916}, "probs_as_returned": {"courier": 0.02334986205840487, "pickup": 0.9458870455791862, "post": 0.004291643013286111, "unknown": 0.026471449349122916}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05379158101277426, "usage": {"input_tokens": 206, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "4976e7b0bf65b476560007aa99fae8bd4c3022880be5b76a6f34bd6624b2132a", "runtime": null}
|
|
|
|
|
{"task_id": "original-extraction-02-0", "family": "extraction", "split": "public", "group": "original-extraction-02", "ts": 1790798643.5923002, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "unknown", "ordinal_ev": null, "probs": {"courier": 0.01060657179917826, "pickup": 0.006836726175654022, "post": 0.011293323016761128, "unknown": 0.9712633790084065}, "probs_as_returned": {"courier": 0.01060657179917826, "pickup": 0.006836726175654022, "post": 0.011293323016761128, "unknown": 0.9712633790084065}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05428420699900016, "usage": {"input_tokens": 207, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "7dfb1da0bfd342524228f4882691655bf50a46bf6c8f4c95baace5e49fbc5b5b", "runtime": null}
|
|
|
|
|
{"task_id": "original-extraction-02-1", "family": "extraction", "split": "public", "group": "original-extraction-02", "ts": 1790798643.653961, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "unknown", "ordinal_ev": null, "probs": {"courier": 0.006844176014044733, "pickup": 0.012037641429207909, "post": 0.008796460047921562, "unknown": 0.9723217225088259}, "probs_as_returned": {"courier": 0.006844176014044733, "pickup": 0.012037641429207909, "post": 0.008796460047921562, "unknown": 0.9723217225088259}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05371831398224458, "usage": {"input_tokens": 207, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "540af746d4c4b85d895bde390a1584ec43ca344bd07ea4fb8c29917105010316", "runtime": null}
|
|
|
|
|
{"task_id": "original-extraction-03-0", "family": "extraction", "split": "public", "group": "original-extraction-03", "ts": 1790798643.716633, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "courier", "ordinal_ev": null, "probs": {"courier": 0.9326330187285887, "pickup": 0.03354563366553508, "post": 0.00423150739028277, "unknown": 0.02958984021559345}, "probs_as_returned": {"courier": 0.9326330187285887, "pickup": 0.03354563366553508, "post": 0.00423150739028277, "unknown": 0.02958984021559345}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.054169485985767096, "usage": {"input_tokens": 211, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "b01b8493dafc625c6f2aef276b33dac6ea2e7af69b39df9675f9ff4955b87cbb", "runtime": null}
|
|
|
|
|
{"task_id": "original-extraction-03-1", "family": "extraction", "split": "public", "group": "original-extraction-03", "ts": 1790798643.7782948, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "courier", "ordinal_ev": null, "probs": {"courier": 0.9787207813254738, "pickup": 0.012116863344787614, "post": 0.0034550659828031225, "unknown": 0.005707289346935534}, "probs_as_returned": {"courier": 0.9787207813254738, "pickup": 0.012116863344787614, "post": 0.0034550659828031225, "unknown": 0.005707289346935534}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05424031399888918, "usage": {"input_tokens": 210, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "fe2a7c07cd72fda0f3c2dac976df9fd27aa700c2746219712ddb2130f0e00794", "runtime": null}
|
|
|
|
|
{"task_id": "original-extraction-04-0", "family": "extraction", "split": "public", "group": "original-extraction-04", "ts": 1790798643.8405502, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "post", "ordinal_ev": null, "probs": {"courier": 0.012648863682625869, "pickup": 0.010478797335157587, "post": 0.9595628201991785, "unknown": 0.017309518783038134}, "probs_as_returned": {"courier": 0.012648863682625869, "pickup": 0.010478797335157587, "post": 0.9595628201991785, "unknown": 0.017309518783038134}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05440111400093883, "usage": {"input_tokens": 208, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "1b23ed2db6d4c636e664d2ed9f003313170e093291bcb5a5d78a3fb39c74b160", "runtime": null}
|
|
|
|
|
{"task_id": "original-extraction-04-1", "family": "extraction", "split": "public", "group": "original-extraction-04", "ts": 1790798643.9040349, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "post", "ordinal_ev": null, "probs": {"courier": 0.03782691951412233, "pickup": 0.013019885086963941, "post": 0.9276461528936708, "unknown": 0.021507042505243032}, "probs_as_returned": {"courier": 0.03782691951412233, "pickup": 0.013019885086963941, "post": 0.9276461528936708, "unknown": 0.021507042505243032}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05442163103725761, "usage": {"input_tokens": 204, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "be08d09d5fc267ef87b19d3c5217f52aa7e7b443b609d539677d5e9ec7c6e3d5", "runtime": null}
|
|
|
|
|
{"task_id": "original-extraction-05-0", "family": "extraction", "split": "public", "group": "original-extraction-05", "ts": 1790798643.9685328, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "unknown", "ordinal_ev": null, "probs": {"courier": 0.013695135711406525, "pickup": 0.007313064273085332, "post": 0.003235134664139037, "unknown": 0.9757566653513692}, "probs_as_returned": {"courier": 0.013695135711406525, "pickup": 0.007313064273085332, "post": 0.003235134664139037, "unknown": 0.9757566653513692}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05464624898741022, "usage": {"input_tokens": 207, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "a2eb05901d26f5a10f55fb2dee391bc204f3e5b4615c8f3b62a5d50a54df56bd", "runtime": null}
|
|
|
|
|
{"task_id": "original-extraction-05-1", "family": "extraction", "split": "public", "group": "original-extraction-05", "ts": 1790798644.0339406, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "unknown", "ordinal_ev": null, "probs": {"courier": 0.01138842444688154, "pickup": 0.005711497827869614, "post": 0.003457613540319971, "unknown": 0.9794424641849289}, "probs_as_returned": {"courier": 0.01138842444688154, "pickup": 0.005711497827869614, "post": 0.003457613540319971, "unknown": 0.9794424641849289}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.055042467021849006, "usage": {"input_tokens": 204, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "90772480e6646d137cfebcd32ff5a678509ba06d3daf463ecb9cd9b79a636379", "runtime": null}
|
|
|
|
|
{"task_id": "original-extraction-06-0", "family": "extraction", "split": "public", "group": "original-extraction-06", "ts": 1790798644.0995572, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "courier", "ordinal_ev": null, "probs": {"courier": 0.9860425408815783, "pickup": 0.003946267989335649, "post": 0.006940756955696869, "unknown": 0.003070434173389162}, "probs_as_returned": {"courier": 0.9860425408815783, "pickup": 0.003946267989335649, "post": 0.006940756955696869, "unknown": 0.003070434173389162}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.056069415993988514, "usage": {"input_tokens": 207, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "8166a617db854184aea784e9f67d319e27babe5f513a4321ec07743b37e903bf", "runtime": null}
|
|
|
|
|
{"task_id": "original-extraction-06-1", "family": "extraction", "split": "public", "group": "original-extraction-06", "ts": 1790798644.1610308, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "courier", "ordinal_ev": null, "probs": {"courier": 0.9707499602252476, "pickup": 0.012018182452518955, "post": 0.00995631722051821, "unknown": 0.007275540101715229}, "probs_as_returned": {"courier": 0.9707499602252476, "pickup": 0.012018182452518955, "post": 0.00995631722051821, "unknown": 0.007275540101715229}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05368592299055308, "usage": {"input_tokens": 207, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "f25be2d66d68e8260580ba163d987577aab9228fc8f54c4d2306cf2950962ef9", "runtime": null}
|
|
|
|
|
{"task_id": "original-adequacy-01-0", "family": "adequacy", "split": "public", "group": "original-adequacy-01", "ts": 1790798644.22398, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "yes", "ordinal_ev": null, "probs": {"yes": 0.91062577829021, "no": 0.08937422170979004}, "probs_as_returned": {"yes": 0.91062577829021, "no": 0.08937422170979004}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05492837296333164, "usage": {"input_tokens": 202, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "31969a6978cefeed45bf5ae1af8acca860b0fce1d19e74797cddb465a7b5a858", "runtime": null}
|
|
|
|
|
{"task_id": "original-adequacy-01-1", "family": "adequacy", "split": "public", "group": "original-adequacy-01", "ts": 1790798644.2840266, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "yes", "ordinal_ev": null, "probs": {"yes": 0.7557061813028185, "no": 0.24429381869718148}, "probs_as_returned": {"yes": 0.7557061813028185, "no": 0.24429381869718148}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.053374308976344764, "usage": {"input_tokens": 198, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "1ce5f478b78b6910177fcf27c22563c391afeb86ea997bfab5251b0076f1a308", "runtime": null}
|
|
|
|
|
{"task_id": "original-adequacy-02-0", "family": "adequacy", "split": "public", "group": "original-adequacy-02", "ts": 1790798644.3461056, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "no", "ordinal_ev": null, "probs": {"yes": 0.00791685353903075, "no": 0.9920831464609693}, "probs_as_returned": {"yes": 0.00791685353903075, "no": 0.9920831464609693}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05387908295961097, "usage": {"input_tokens": 199, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "13577f760c0fa21a3cef6ad50f31bbcc72ce72588a367d29ddcd628e7f18ad27", "runtime": null}
|
|
|
|
|
{"task_id": "original-adequacy-02-1", "family": "adequacy", "split": "public", "group": "original-adequacy-02", "ts": 1790798644.4077055, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "no", "ordinal_ev": null, "probs": {"yes": 0.006989802244620407, "no": 0.9930101977553796}, "probs_as_returned": {"yes": 0.006989802244620407, "no": 0.9930101977553796}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05366035597398877, "usage": {"input_tokens": 199, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "82a89d82d38ecb665c788484dbc37d0a3081d419aae3a4bee84c1697c67811f1", "runtime": null}
|
|
|
|
|
{"task_id": "original-adequacy-03-0", "family": "adequacy", "split": "public", "group": "original-adequacy-03", "ts": 1790798644.4726694, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "no", "ordinal_ev": null, "probs": {"yes": 0.08937422170979005, "no": 0.91062577829021}, "probs_as_returned": {"yes": 0.08937422170979005, "no": 0.91062577829021}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05446359299821779, "usage": {"input_tokens": 201, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "8c6706cf1986fb21c64b70413b048a6bc1b0973999047cb67e99bb2ba67fb8e2", "runtime": null}
|
|
|
|
|
{"task_id": "original-adequacy-03-1", "family": "adequacy", "split": "public", "group": "original-adequacy-03", "ts": 1790798644.5364928, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "no", "ordinal_ev": null, "probs": {"yes": 0.06310763191560703, "no": 0.936892368084393}, "probs_as_returned": {"yes": 0.06310763191560703, "no": 0.936892368084393}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05383687000721693, "usage": {"input_tokens": 205, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "7265fff5f9588504c43064688ed70eb458d2c641908c9b65b3c48c2cad6f92ee", "runtime": null}
|
|
|
|
|
{"task_id": "original-adequacy-04-0", "family": "adequacy", "split": "public", "group": "original-adequacy-04", "ts": 1790798644.60003, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "yes", "ordinal_ev": null, "probs": {"yes": 0.9471470189565372, "no": 0.05285298104346281}, "probs_as_returned": {"yes": 0.9471470189565372, "no": 0.05285298104346281}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05417428398504853, "usage": {"input_tokens": 205, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "8d7fc5ad0ad40e1df9fb2b82cb1e622a13d1ea97c5fdfed5b0b4f999099c8c08", "runtime": null}
|
|
|
|
|
{"task_id": "original-adequacy-04-1", "family": "adequacy", "split": "public", "group": "original-adequacy-04", "ts": 1790798644.6614974, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "yes", "ordinal_ev": null, "probs": {"yes": 0.8940776460411956, "no": 0.10592235395880445}, "probs_as_returned": {"yes": 0.8940776460411956, "no": 0.10592235395880445}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05334242701064795, "usage": {"input_tokens": 202, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "3efa4116ed7f7f62b686ec4dfd97fd71e5dc9f2ac9c1e5deedc7ac13f2807bb9", "runtime": null}
|
|
|
|
|
{"task_id": "original-adequacy-05-0", "family": "adequacy", "split": "public", "group": "original-adequacy-05", "ts": 1790798644.7243233, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "no", "ordinal_ev": null, "probs": {"yes": 0.11840617139815589, "no": 0.8815938286018441}, "probs_as_returned": {"yes": 0.11840617139815589, "no": 0.8815938286018441}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.054711906996089965, "usage": {"input_tokens": 195, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "f5cfae2e4b77b646cd4eb46a3291993d21071aabad1a807a44a42c1b02492186", "runtime": null}
|
|
|
|
|
{"task_id": "original-adequacy-05-1", "family": "adequacy", "split": "public", "group": "original-adequacy-05", "ts": 1790798644.7872107, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "no", "ordinal_ev": null, "probs": {"yes": 0.03267757061976492, "no": 0.967322429380235}, "probs_as_returned": {"yes": 0.03267757061976492, "no": 0.967322429380235}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05378155503422022, "usage": {"input_tokens": 195, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "7eb2fb247465d1b6ac95cf15915ff6801ca01688fe736d831702daba54882f1a", "runtime": null}
|
|
|
|
|
{"task_id": "original-adequacy-06-0", "family": "adequacy", "split": "public", "group": "original-adequacy-06", "ts": 1790798644.8507006, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "yes", "ordinal_ev": null, "probs": {"yes": 0.9583890938912367, "no": 0.04161090610876328}, "probs_as_returned": {"yes": 0.9583890938912367, "no": 0.04161090610876328}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.054155079007614404, "usage": {"input_tokens": 211, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "6dce49eafd7f528d920b3e3a10673d94dbebeff5ca21e8ea8528f67585ccb82c", "runtime": null}
|
|
|
|
|
{"task_id": "original-adequacy-06-1", "family": "adequacy", "split": "public", "group": "original-adequacy-06", "ts": 1790798644.913032, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "yes", "ordinal_ev": null, "probs": {"yes": 0.5930110454411601, "no": 0.4069889545588399}, "probs_as_returned": {"yes": 0.5930110454411601, "no": 0.4069889545588399}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.0544490980100818, "usage": {"input_tokens": 212, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "ea56f2eaff430be6c078e57bde72ae7b3f110403986414c2bab40b393118d213", "runtime": null}
|
|
|
|
|
{"task_id": "original-routing-01-0", "family": "routing", "split": "public", "group": "original-routing-01", "ts": 1790798644.9759166, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "math", "ordinal_ev": null, "probs": {"coding": 0.030403476101725994, "coding_agent": 0.005588078139470822, "document": 0.0029839776552908095, "general": 0.05693642518396949, "math": 0.9000045761395922, "tools": 0.004083466779950801}, "probs_as_returned": {"coding": 0.030403476101725994, "coding_agent": 0.005588078139470822, "document": 0.0029839776552908095, "general": 0.05693642518396949, "math": 0.9000045761395922, "tools": 0.004083466779950801}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.054466863977722824, "usage": {"input_tokens": 248, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "14cc6e748f17c17d6bb73c2202525ae59a4aa1a5ef0fb5348d1732476d657eea", "runtime": null}
|
|
|
|
|
{"task_id": "original-routing-01-1", "family": "routing", "split": "public", "group": "original-routing-01", "ts": 1790798645.0399191, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "math", "ordinal_ev": null, "probs": {"coding": 0.027064128848065867, "coding_agent": 0.006004452348212528, "document": 0.004120910951392922, "general": 0.05068284732390288, "math": 0.9082573436250052, "tools": 0.003870316903420689}, "probs_as_returned": {"coding": 0.027064128848065867, "coding_agent": 0.006004452348212528, "document": 0.004120910951392922, "general": 0.05068284732390288, "math": 0.9082573436250052, "tools": 0.003870316903420689}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05466922902269289, "usage": {"input_tokens": 244, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "21c1b1db6d69563819b5a162e5465d02f003e37437bce870ca0a13c5f8c84fa3", "runtime": null}
|
|
|
|
|
{"task_id": "original-routing-02-0", "family": "routing", "split": "public", "group": "original-routing-02", "ts": 1790798645.1029978, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "coding", "ordinal_ev": null, "probs": {"coding": 0.9415619813564295, "coding_agent": 0.018084528998433786, "document": 0.01595195139756404, "general": 0.02050220621528298, "math": 0.0024289187126925386, "tools": 0.0014704133195969841}, "probs_as_returned": {"coding": 0.9415619813564295, "coding_agent": 0.018084528998433786, "document": 0.01595195139756404, "general": 0.02050220621528298, "math": 0.0024289187126925386, "tools": 0.0014704133195969841}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.054412967001553625, "usage": {"input_tokens": 249, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "9ed5307eb596123ef740ff863371e07b0df242d993c0d0d0e5eba47191811f10", "runtime": null}
|
|
|
|
|
{"task_id": "original-routing-02-1", "family": "routing", "split": "public", "group": "original-routing-02", "ts": 1790798645.1660168, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "coding", "ordinal_ev": null, "probs": {"coding": 0.973635359123508, "coding_agent": 0.008272706167638342, "document": 0.004703566958129719, "general": 0.00998591082769865, "math": 0.0023589227246364557, "tools": 0.0010435341983889071}, "probs_as_returned": {"coding": 0.973635359123508, "coding_agent": 0.008272706167638342, "document": 0.004703566958129719, "general": 0.00998591082769865, "math": 0.0023589227246364557, "tools": 0.0010435341983889071}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05468420998658985, "usage": {"input_tokens": 243, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "127cb6d50f4be500f215e63ab40b40e87f8bb02bd0063a85bbe4839f9a79fe75", "runtime": null}
|
|
|
|
|
{"task_id": "original-routing-03-0", "family": "routing", "split": "public", "group": "original-routing-03", "ts": 1790798645.2300868, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "coding_agent", "ordinal_ev": null, "probs": {"coding": 0.013544661981601466, "coding_agent": 0.9650356763230314, "document": 0.003406754965701558, "general": 0.00873054421930428, "math": 0.0024894731036984113, "tools": 0.006792889406662867}, "probs_as_returned": {"coding": 0.013544661981601466, "coding_agent": 0.9650356763230314, "document": 0.003406754965701558, "general": 0.00873054421930428, "math": 0.0024894731036984113, "tools": 0.006792889406662867}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.054468941991217434, "usage": {"input_tokens": 248, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "81d43fdb41c2d58f42638075da6c9188970b67ca93d1f26ca5c5a03ed688527e", "runtime": null}
|
|
|
|
|
{"task_id": "original-routing-03-1", "family": "routing", "split": "public", "group": "original-routing-03", "ts": 1790798645.2928548, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "coding_agent", "ordinal_ev": null, "probs": {"coding": 0.015370445312191146, "coding_agent": 0.9659803493932506, "document": 0.0038659763929818373, "general": 0.009304926219392514, "math": 0.0028250473602176632, "tools": 0.002653255321966199}, "probs_as_returned": {"coding": 0.015370445312191146, "coding_agent": 0.9659803493932506, "document": 0.0038659763929818373, "general": 0.009304926219392514, "math": 0.0028250473602176632, "tools": 0.002653255321966199}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05446531600318849, "usage": {"input_tokens": 250, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "9d6d5e3f25514c8a5fb909dc45beab021167b90249fc66ad0184ce4005cf7bf0", "runtime": null}
|
|
|
|
|
{"task_id": "original-routing-04-0", "family": "routing", "split": "public", "group": "original-routing-04", "ts": 1790798645.3546, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "document", "ordinal_ev": null, "probs": {"coding": 0.014210229746939956, "coding_agent": 0.022045907219979437, "document": 0.7877520218832728, "general": 0.14478674264730218, "math": 0.004593678879467563, "tools": 0.02661141962303802}, "probs_as_returned": {"coding": 0.014210229746939956, "coding_agent": 0.022045907219979437, "document": 0.7877520218832728, "general": 0.14478674264730218, "math": 0.004593678879467563, "tools": 0.02661141962303802}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.053562437009532005, "usage": {"input_tokens": 244, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "407b34b8607d81f907ea3f14b2a92e0380ccee83480165f2eb59df45c23608c7", "runtime": null}
|
|
|
|
|
{"task_id": "original-routing-04-1", "family": "routing", "split": "public", "group": "original-routing-04", "ts": 1790798645.4174123, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "document", "ordinal_ev": null, "probs": {"coding": 0.024413533876144627, "coding_agent": 0.027677322136038972, "document": 0.6787431213908676, "general": 0.24874727547479406, "math": 0.006538077731369333, "tools": 0.013880669390785366}, "probs_as_returned": {"coding": 0.024413533876144627, "coding_agent": 0.027677322136038972, "document": 0.6787431213908676, "general": 0.24874727547479406, "math": 0.006538077731369333, "tools": 0.013880669390785366}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.054366908967494965, "usage": {"input_tokens": 243, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "e6a82a2f877bb3b3f62f5ba5e8c73c1c79bfd640427f17b27c43b804e158bf72", "runtime": null}
|
|
|
|
|
{"task_id": "original-routing-05-0", "family": "routing", "split": "public", "group": "original-routing-05", "ts": 1790798645.481739, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "tools", "ordinal_ev": null, "probs": {"coding": 0.013819082412644958, "coding_agent": 0.011448251071317058, "document": 0.021439076042707273, "general": 0.08005466995874373, "math": 0.004756477464671993, "tools": 0.868482443049915}, "probs_as_returned": {"coding": 0.013819082412644958, "coding_agent": 0.011448251071317058, "document": 0.021439076042707273, "general": 0.08005466995874373, "math": 0.004756477464671993, "tools": 0.868482443049915}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05526974599342793, "usage": {"input_tokens": 245, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "4e5dac3edc224500f320d2e62f6c10d80c28daff2baa33d340c75a75ab4e2d9f", "runtime": null}
|
|
|
|
|
{"task_id": "original-routing-05-1", "family": "routing", "split": "public", "group": "original-routing-05", "ts": 1790798645.543847, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "tools", "ordinal_ev": null, "probs": {"coding": 0.01907649307568939, "coding_agent": 0.014842661214610822, "document": 0.013940073466224478, "general": 0.26598655114071845, "math": 0.004506346432653027, "tools": 0.6816478746701038}, "probs_as_returned": {"coding": 0.01907649307568939, "coding_agent": 0.014842661214610822, "document": 0.013940073466224478, "general": 0.26598655114071845, "math": 0.004506346432653027, "tools": 0.6816478746701038}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05381619097897783, "usage": {"input_tokens": 245, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "8fd1f9d74a59e501935aca0af05667ef36e0d87425b524ee8e7d2bde5c588fcc", "runtime": null}
|
|
|
|
|
{"task_id": "original-routing-06-0", "family": "routing", "split": "public", "group": "original-routing-06", "ts": 1790798645.6058424, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "general", "ordinal_ev": null, "probs": {"coding": 0.022131200140044424, "coding_agent": 0.009194990510311016, "document": 0.06038820440582165, "general": 0.8965198972789722, "math": 0.0071542561880119735, "tools": 0.0046114514768386536}, "probs_as_returned": {"coding": 0.022131200140044424, "coding_agent": 0.009194990510311016, "document": 0.06038820440582165, "general": 0.8965198972789722, "math": 0.0071542561880119735, "tools": 0.0046114514768386536}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05420429399237037, "usage": {"input_tokens": 243, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "3892709482c6859d667344af9f8848373040659352ec3f2f4237f53057319cd0", "runtime": null}
|
|
|
|
|
{"task_id": "original-routing-06-1", "family": "routing", "split": "public", "group": "original-routing-06", "ts": 1790798645.6680808, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "general", "ordinal_ev": null, "probs": {"coding": 0.02223904433233792, "coding_agent": 0.009239796877608073, "document": 0.05352662420536432, "general": 0.9008885827216597, "math": 0.008150214081207844, "tools": 0.005955737781822105}, "probs_as_returned": {"coding": 0.02223904433233792, "coding_agent": 0.009239796877608073, "document": 0.05352662420536432, "general": 0.9008885827216597, "math": 0.008150214081207844, "tools": 0.005955737781822105}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05373023898573592, "usage": {"input_tokens": 243, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "e51ba52649cc5cc5e5f97096a34c0f6b3dbf377f0a4c739005f2d597dd7f0070", "runtime": null}
|
|
|
|
|
{"task_id": "hard-opus-a-long_policy-01", "family": "long_policy", "split": "public", "group": "hard-opus-a-long_policy-01", "ts": 1790798652.381662, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "pay_subject_to_15000_sublimit", "ordinal_ev": null, "probs": {"deny_repeated_seepage": 0.01738839593866782, "deny_vacancy_exclusion": 0.02098937905094514, "pay_full_estimate_less_deductible": 0.006785144709800851, "pay_subject_to_10000_sublimit": 0.1562765432073203, "pay_subject_to_15000_sublimit": 0.7985605370932659}, "probs_as_returned": {"deny_repeated_seepage": 0.01738839593866782, "deny_vacancy_exclusion": 0.02098937905094514, "pay_full_estimate_less_deductible": 0.006785144709800851, "pay_subject_to_10000_sublimit": 0.1562765432073203, "pay_subject_to_15000_sublimit": 0.7985605370932659}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 6.7012044949806295, "usage": {"input_tokens": 4074, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "56aa987138ced15bb52c53de69f012f4c815e4a6f3a30e90a712be43c23b3120", "runtime": null}
|
|
|
|
|
{"task_id": "hard-opus-a-long_policy-04", "family": "long_policy", "split": "public", "group": "hard-opus-a-long_policy-04", "ts": 1790798652.5372088, "status": "ok", "ok": true, "valid": true, "correct": false, "predicted": "vp_and_finance_director", "ordinal_ev": null, "probs": {"budget_holder": 0.02271616887362895, "cfo": 0.08482339827852999, "department_head": 0.08482339827852999, "executive_committee": 0.045294839737184185, "vp_and_finance_director": 0.7623421948321268}, "probs_as_returned": {"budget_holder": 0.02271616887362895, "cfo": 0.08482339827852999, "department_head": 0.08482339827852999, "executive_committee": 0.045294839737184185, "vp_and_finance_director": 0.7623421948321268}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.14177889103302732, "usage": {"input_tokens": 2764, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "abbc0d76d92c11de491cacbf425cc6c5eeb0b8ca4118b49321f575876590fc06", "runtime": null}
|
|
|
|
|
{"task_id": "hard-opus-a-long_policy-08", "family": "long_policy", "split": "public", "group": "hard-opus-a-long_policy-08", "ts": 1790798652.6846776, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "parts_covered_labour_charged", "ordinal_ev": null, "probs": {"full_repair_no_charge": 0.06519889343118179, "not_covered": 0.016398833394742487, "parts_covered_labour_charged": 0.9090784780802361, "pro_rata_replacement_credit": 0.009323795093839524}, "probs_as_returned": {"full_repair_no_charge": 0.06519889343118179, "not_covered": 0.016398833394742487, "parts_covered_labour_charged": 0.9090784780802361, "pro_rata_replacement_credit": 0.009323795093839524}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.13272097101435065, "usage": {"input_tokens": 2524, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "9eadfae802e654544596f3ff6f45d6d26ea6acbb86c1bcbeb995cddaaf19c5d5", "runtime": null}
|
|
|
|
|
{"task_id": "hard-opus-a-long_policy-09", "family": "long_policy", "split": "public", "group": "hard-opus-a-long_policy-09", "ts": 1790798652.8359427, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "license_required", "ordinal_ev": null, "probs": {"license_exception_lvs": 0.114786494715961, "license_required": 0.8026723665682973, "no_license_required": 0.047691072005070445, "shipment_prohibited": 0.034850066710671174}, "probs_as_returned": {"license_exception_lvs": 0.114786494715961, "license_required": 0.8026723665682973, "no_license_required": 0.047691072005070445, "shipment_prohibited": 0.034850066710671174}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.1372749170404859, "usage": {"input_tokens": 2662, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "1788cf4b66f1a7a036b5b7c386702913e72c92597020cf4a246df0a02b08a05a", "runtime": null}
|
|
|
|
|
{"task_id": "hard-opus-a-long_policy-11", "family": "long_policy", "split": "public", "group": "hard-opus-a-long_policy-11", "ts": 1790798652.977517, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "yes", "ordinal_ev": null, "probs": {"yes": 0.5930110454411601, "no": 0.4069889545588399}, "probs_as_returned": {"yes": 0.5930110454411601, "no": 0.4069889545588399}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.1279204820166342, "usage": {"input_tokens": 2470, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "54eb90c2da5fb15954a73d7058e3c09344d6420d05c09e185b5a87049555f2f9", "runtime": null}
|
|
|
|
|
{"task_id": "hard-opus-a-long_policy-13", "family": "long_policy", "split": "public", "group": "hard-opus-a-long_policy-13", "ts": 1790798653.122362, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "yes", "ordinal_ev": null, "probs": {"yes": 0.7064759712765732, "no": 0.29352402872342676}, "probs_as_returned": {"yes": 0.7064759712765732, "no": 0.29352402872342676}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.1299751169863157, "usage": {"input_tokens": 2559, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "2a7e1458e71b1b0d41118380f3eeffe88ef6539e5485a461c008b2b668d11715", "runtime": null}
|
|
|
|
|
{"task_id": "hard-opus-a-long_policy-17", "family": "long_policy", "split": "public", "group": "hard-opus-a-long_policy-17", "ts": 1790798653.264856, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "database_oncall", "ordinal_ev": null, "probs": {"database_oncall": 0.8353888582269757, "no_page_ticket_only": 0.07232152988407799, "platform_oncall": 0.03861896981172954, "security_incident_response": 0.04963493453981136, "vendor_support": 0.004035707537405349}, "probs_as_returned": {"database_oncall": 0.8353888582269757, "no_page_ticket_only": 0.07232152988407799, "platform_oncall": 0.03861896981172954, "security_incident_response": 0.04963493453981136, "vendor_support": 0.004035707537405349}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.1281475349678658, "usage": {"input_tokens": 2494, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "2f7cc97856cb0a3a800fb6123d93990ae071b13eacbe4651124e591e44bad85d", "runtime": null}
|
|
|
|
|
{"task_id": "hard-opus-a-long_policy-19", "family": "long_policy", "split": "public", "group": "hard-opus-a-long_policy-19", "ts": 1790798653.403023, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "no", "ordinal_ev": null, "probs": {"yes": 0.37709365395745764, "no": 0.6229063460425424}, "probs_as_returned": {"yes": 0.37709365395745764, "no": 0.6229063460425424}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.12492617400130257, "usage": {"input_tokens": 2465, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "13bbb7c51ad82c05b8325ddc909242847759d221f838a0e03d1db7def38b8dfd", "runtime": null}
|
|
|
|
|
{"task_id": "hard-opus-a-probability-03", "family": "probability", "split": "public", "group": "hard-opus-a-probability-03", "ts": 1790798653.4728336, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "yes", "ordinal_ev": null, "probs": {"yes": 0.5777854893190272, "no": 0.4222145106809728}, "probs_as_returned": {"yes": 0.5777854893190272, "no": 0.4222145106809728}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05797434796113521, "usage": {"input_tokens": 544, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "6d06bb50e25d0558fa93dcbc64bf5fa746a451736dc29f08cc62176aaf2cd0a6", "runtime": null}
|
|
|
|
|
{"task_id": "hard-opus-a-probability-04", "family": "probability", "split": "public", "group": "hard-opus-a-probability-04", "ts": 1790798653.5602965, "status": "ok", "ok": true, "valid": true, "correct": false, "predicted": "late", "ordinal_ev": null, "probs": {"early": 0.13202257175482904, "late": 0.7183050733055719, "on_time": 0.149672354939599}, "probs_as_returned": {"early": 0.13202257175482904, "late": 0.7183050733055719, "on_time": 0.149672354939599}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.07543992198770866, "usage": {"input_tokens": 1215, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "72eba10e338fec996be8ca11dd36aa4e619cd34df714b8ee82439260b0e80195", "runtime": null}
|
|
|
|
|
{"task_id": "hard-opus-a-probability-07", "family": "probability", "split": "public", "group": "hard-opus-a-probability-07", "ts": 1790798653.6626265, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "escalated", "ordinal_ev": null, "probs": {"escalated": 0.6010911219225122, "reopened": 0.09745097270141673, "resolved_first_contact": 0.30145790537607103}, "probs_as_returned": {"escalated": 0.6010911219225122, "reopened": 0.09745097270141673, "resolved_first_contact": 0.30145790537607103}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.09108415700029582, "usage": {"input_tokens": 1329, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "085f78bd7551381dc9e218e06058a5cca334baa938f674a48aca0af0941ed07a", "runtime": null}
|
|
|
|
|
{"task_id": "hard-opus-a-probability-08", "family": "probability", "split": "public", "group": "hard-opus-a-probability-08", "ts": 1790798653.7338297, "status": "ok", "ok": true, "valid": true, "correct": false, "predicted": "yes", "ordinal_ev": null, "probs": {"yes": 0.6229063460425425, "no": 0.37709365395745753}, "probs_as_returned": {"yes": 0.6229063460425425, "no": 0.37709365395745753}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.06035748997237533, "usage": {"input_tokens": 504, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "cac4848f95fdff954264a798a22a8ff5731e0161f81a14e7b3ead334a870c027", "runtime": null}
|
|
|
|
|
{"task_id": "hard-opus-a-temporal_numeric-03", "family": "temporal_numeric", "split": "public", "group": "hard-opus-a-temporal_numeric-03", "ts": 1790798653.8066118, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "yes", "ordinal_ev": null, "probs": {"yes": 0.7318060856600669, "no": 0.2681939143399331}, "probs_as_returned": {"yes": 0.7318060856600669, "no": 0.2681939143399331}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.0629730080254376, "usage": {"input_tokens": 600, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "b7b61d6bd490ea1e6ea1a57ca63ae819dbf8e33a5ab919ee5dc99e15e118b20a", "runtime": null}
|
|
|
|
|
{"task_id": "hard-opus-a-temporal_numeric-06", "family": "temporal_numeric", "split": "public", "group": "hard-opus-a-temporal_numeric-06", "ts": 1790798653.8787274, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "no", "ordinal_ev": null, "probs": {"yes": 0.12511350509772579, "no": 0.8748864949022742}, "probs_as_returned": {"yes": 0.12511350509772579, "no": 0.8748864949022742}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.06183091801358387, "usage": {"input_tokens": 635, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "31cb0da7913f9c605c44cf79f289dca79d8ba630817a12ec94e972d21aba1db4", "runtime": null}
|
|
|
|
|
{"task_id": "hard-opus-a-temporal_numeric-07", "family": "temporal_numeric", "split": "public", "group": "hard-opus-a-temporal_numeric-07", "ts": 1790798653.9747002, "status": "ok", "ok": true, "valid": true, "correct": false, "predicted": "sep_25", "ordinal_ev": null, "probs": {"sep_24": 0.1443341310190758, "sep_25": 0.3262691984686731, "sep_26": 0.1855050950995479, "sep_27": 0.2384199630201128, "sep_28": 0.10547161239259041}, "probs_as_returned": {"sep_24": 0.1443341310190758, "sep_25": 0.3262691984686731, "sep_26": 0.1855050950995479, "sep_27": 0.2384199630201128, "sep_28": 0.10547161239259041}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.08721445500850677, "usage": {"input_tokens": 1418, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "919e548b2fb2e1aa07ec01eb7247a21df2328783f9052ba9b15d9119c1636f4a", "runtime": null}
|
|
|
|
|
{"task_id": "hard-opus-a-temporal_numeric-09", "family": "temporal_numeric", "split": "public", "group": "hard-opus-a-temporal_numeric-09", "ts": 1790798654.0460198, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "no", "ordinal_ev": null, "probs": {"yes": 0.42221451068097277, "no": 0.5777854893190273}, "probs_as_returned": {"yes": 0.42221451068097277, "no": 0.5777854893190273}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.06131254998035729, "usage": {"input_tokens": 635, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "81df3a132ad391039cf5334276ec7cbd8f5b57d4c10544b54f901afc6c7e0be4", "runtime": null}
|
|
|
|
|
{"task_id": "hard-opus-a-temporal_numeric-12", "family": "temporal_numeric", "split": "public", "group": "hard-opus-a-temporal_numeric-12", "ts": 1790798654.1166303, "status": "ok", "ok": true, "valid": true, "correct": false, "predicted": "3", "ordinal_ev": 2.102096986624212, "probs": {"0": 0.11983544620580835, "1": 0.10570411896691179, "2": 0.3269884368245393, "3": 0.4474719980027406}, "probs_as_returned": {"0": 0.11983544620580835, "1": 0.10570411896691179, "2": 0.3269884368245393, "3": 0.4474719980027406}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.06037570897024125, "usage": {"input_tokens": 708, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "6fc66942d85e517ba67fe4658cf7994c9e20c6b3f8d6e6607da3273f6133057c", "runtime": null}
|
|
|
|
|
{"task_id": "hard-opus-b-ambiguous-02", "family": "ambiguous", "split": "public", "group": "hard-opus-b-ambiguous-02", "ts": 1790798654.1896152, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "real_incident", "ordinal_ev": null, "probs": {"cannot_determine": 0.02744828681074916, "false_positive": 0.05140225590652218, "real_incident": 0.9211494572827287}, "probs_as_returned": {"cannot_determine": 0.02744828681074916, "false_positive": 0.05140225590652218, "real_incident": 0.9211494572827287}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.062126367003656924, "usage": {"input_tokens": 654, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "db6ba6fc8430f9ee4107de166f2ee70592eb58c31ca1cfec0659ecb71d2a9325", "runtime": null}
|
|
|
|
|
{"task_id": "hard-opus-b-ambiguous-03", "family": "ambiguous", "split": "public", "group": "hard-opus-b-ambiguous-03", "ts": 1790798654.2614846, "status": "ok", "ok": true, "valid": true, "correct": false, "predicted": "within_limitation", "ordinal_ev": null, "probs": {"insufficient_information": 0.04935003802520305, "time_barred": 0.30439788588738664, "within_limitation": 0.6462520760874103}, "probs_as_returned": {"insufficient_information": 0.04935003802520305, "time_barred": 0.30439788588738664, "within_limitation": 0.6462520760874103}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.06198942702030763, "usage": {"input_tokens": 606, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "861f7cf32ade0a16488880d048d82d3d48682e905d861e999d8e29e0c2b5aa20", "runtime": null}
|
|
|
|
|
{"task_id": "hard-opus-b-ambiguous-07", "family": "ambiguous", "split": "public", "group": "hard-opus-b-ambiguous-07", "ts": 1790798654.332647, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "within_policy", "ordinal_ev": null, "probs": {"insufficient_information": 0.04206359082164066, "over_limit": 0.33346268046304034, "within_policy": 0.624473728715319}, "probs_as_returned": {"insufficient_information": 0.04206359082164066, "over_limit": 0.33346268046304034, "within_policy": 0.624473728715319}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.06203041999833658, "usage": {"input_tokens": 608, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "eb7a6b4833792f48f079247fb6b1fa9196618a36c194c1a1f01a3ef7a4858361", "runtime": null}
|
|
|
|
|
{"task_id": "hard-opus-b-ambiguous-09", "family": "ambiguous", "split": "public", "group": "hard-opus-b-ambiguous-09", "ts": 1790798654.404011, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "legitimate", "ordinal_ev": null, "probs": {"compromised": 0.052277255306895254, "inconclusive": 0.010892947754565218, "legitimate": 0.9368297969385395}, "probs_as_returned": {"compromised": 0.052277255306895254, "inconclusive": 0.010892947754565218, "legitimate": 0.9368297969385395}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.061056497041136026, "usage": {"input_tokens": 747, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "ea594e8ae7c7c5150605b472196c7ce1a4296b57e9712daf4faebcb2653d7e02", "runtime": null}
|
|
|
|
|
{"task_id": "hard-opus-b-ambiguous-10", "family": "ambiguous", "split": "public", "group": "hard-opus-b-ambiguous-10", "ts": 1790798654.476039, "status": "ok", "ok": true, "valid": true, "correct": false, "predicted": "send_to_alex_moreno", "ordinal_ev": null, "probs": {"ask_user_which_alex": 0.21763025953150913, "send_to_alex_moreno": 0.6732242882994754, "send_to_alexandra_lind": 0.10914545216901542}, "probs_as_returned": {"ask_user_which_alex": 0.21763025953150913, "send_to_alex_moreno": 0.6732242882994754, "send_to_alexandra_lind": 0.10914545216901542}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.06286407797597349, "usage": {"input_tokens": 666, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "34a8239a2cb113abbce415811c60bc1b915e334fb782d2968a5248fa40d478e3", "runtime": null}
|
|
|
|
|
{"task_id": "hard-opus-b-ambiguous-11", "family": "ambiguous", "split": "public", "group": "hard-opus-b-ambiguous-11", "ts": 1790798654.5439198, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "cannot_determine", "ordinal_ev": null, "probs": {"cannot_determine": 0.9499639519924629, "grade_correct": 0.02345050282102886, "grade_should_be_higher": 0.026585545186508176}, "probs_as_returned": {"cannot_determine": 0.9499639519924629, "grade_correct": 0.02345050282102886, "grade_should_be_higher": 0.026585545186508176}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.058465356996748596, "usage": {"input_tokens": 574, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "20871cc21ca7fc78f62a445f4202c96bb5c51aa6db2ab5aeea07a25a064bce27", "runtime": null}
|
|
|
|
|
{"task_id": "hard-opus-b-ambiguous-13", "family": "ambiguous", "split": "public", "group": "hard-opus-b-ambiguous-13", "ts": 1790798654.6149995, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "cannot_determine", "ordinal_ev": null, "probs": {"cannot_determine": 0.9775256664330146, "charge_data_team": 0.01371996433710697, "charge_platform_team": 0.0026849668364085587, "split_50_50": 0.006069402393469905}, "probs_as_returned": {"cannot_determine": 0.9775256664330146, "charge_data_team": 0.01371996433710697, "charge_platform_team": 0.0026849668364085587, "split_50_50": 0.006069402393469905}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.06058689201017842, "usage": {"input_tokens": 717, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "0070361cc320cdfccd8f71dfd8921448e7d23da232d9427d81d6e0670b446644", "runtime": null}
|
|
|
|
|
{"task_id": "hard-opus-b-multi_hop-03", "family": "multi_hop", "split": "public", "group": "hard-opus-b-multi_hop-03", "ts": 1790798654.7835927, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "tier3_cfo", "ordinal_ev": null, "probs": {"tier1_team_lead": 0.0497521079639966, "tier2_department_head": 0.17447988465360076, "tier3_cfo": 0.6118982972031438, "tier4_board": 0.16386971017925878}, "probs_as_returned": {"tier1_team_lead": 0.0497521079639966, "tier2_department_head": 0.17447988465360076, "tier3_cfo": 0.6118982972031438, "tier4_board": 0.16386971017925878}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.1560023670317605, "usage": {"input_tokens": 3091, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "39e49dad145d39aa3bb6e959d413bf22b8e20bfe2778a9ebc279230f1d9aa3c8", "runtime": null}
|
|
|
|
|
{"task_id": "hard-opus-b-multi_hop-04", "family": "multi_hop", "split": "public", "group": "hard-opus-b-multi_hop-04", "ts": 1790798654.9268181, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "bjorn", "ordinal_ev": null, "probs": {"ana": 0.10338450001046608, "bjorn": 0.5624917858876448, "chen": 0.05520628309044809, "dmitri": 0.14147799705200356, "esra": 0.040341777170236494, "no_page_ticket_only": 0.09709765678920096}, "probs_as_returned": {"ana": 0.10338450001046608, "bjorn": 0.5624917858876448, "chen": 0.05520628309044809, "dmitri": 0.14147799705200356, "esra": 0.040341777170236494, "no_page_ticket_only": 0.09709765678920096}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.1283320359652862, "usage": {"input_tokens": 2490, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "3a4f89a0b1f8f364ad1ffcc8137a37fb75f26e623327a842dd6df20d097b6d1a", "runtime": null}
|
|
|
|
|
{"task_id": "hard-opus-b-multi_hop-05", "family": "multi_hop", "split": "public", "group": "hard-opus-b-multi_hop-05", "ts": 1790798655.0801845, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "2", "ordinal_ev": 2.3268150682115487, "probs": {"0": 0.02658575966524453, "1": 0.12758992856431356, "2": 0.3946907024781775, "3": 0.3946907024781775, "4": 0.056442906814086966}, "probs_as_returned": {"0": 0.02658575966524453, "1": 0.12758992856431356, "2": 0.3946907024781775, "3": 0.3946907024781775, "4": 0.056442906814086966}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.1396679500467144, "usage": {"input_tokens": 2721, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "c3c6daab6aac5bd9034a8ea083b87b00ecba42011208b1d484108d198e37c606", "runtime": null}
|
|
|
|
|
{"task_id": "hard-opus-b-multi_hop-07", "family": "multi_hop", "split": "public", "group": "hard-opus-b-multi_hop-07", "ts": 1790798655.2459743, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "credit_20_percent", "ordinal_ev": null, "probs": {"credit_10_percent": 0.017590746089182055, "credit_20_percent": 0.5207217809221588, "credit_25_percent": 0.12300755553854442, "credit_50_percent": 0.2960639325196957, "credit_full_month": 0.039764112150960935, "no_credit": 0.0028518727794581552}, "probs_as_returned": {"credit_10_percent": 0.017590746089182055, "credit_20_percent": 0.5207217809221588, "credit_25_percent": 0.12300755553854442, "credit_50_percent": 0.2960639325196957, "credit_full_month": 0.039764112150960935, "no_credit": 0.0028518727794581552}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.15285225899424404, "usage": {"input_tokens": 2779, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "58636ec4969b87da9e4a1a27b1c4ed59200c09a1d7cf759102525a295b0719ae", "runtime": null}
|
|
|
|
|
{"task_id": "hard-opus-b-multi_hop-08", "family": "multi_hop", "split": "public", "group": "hard-opus-b-multi_hop-08", "ts": 1790798655.3868036, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "no", "ordinal_ev": null, "probs": {"yes": 0.12511350509772579, "no": 0.8748864949022742}, "probs_as_returned": {"yes": 0.12511350509772579, "no": 0.8748864949022742}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.12717864196747541, "usage": {"input_tokens": 2452, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "cb2691a2675346fdf13c7958793e9151169dced620393a061b1b0bc5f2f7d1ee", "runtime": null}
|
|
|
|
|
{"task_id": "hard-opus-b-probability-01", "family": "probability", "split": "public", "group": "hard-opus-b-probability-01", "ts": 1790798655.5036876, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "merchant_wins", "ordinal_ev": null, "probs": {"customer_wins": 0.14739129143438487, "customer_withdraws": 0.2286644595678006, "merchant_wins": 0.6239442489978145}, "probs_as_returned": {"customer_wins": 0.14739129143438487, "customer_withdraws": 0.2286644595678006, "merchant_wins": 0.6239442489978145}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.10605209600180387, "usage": {"input_tokens": 2032, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "954a4563ac88067078b3e5a3b51bd0e23391e835dde3fa8eb8825377f3658183", "runtime": null}
|
|
|
|
|
{"task_id": "hard-opus-b-probability-02", "family": "probability", "split": "public", "group": "hard-opus-b-probability-02", "ts": 1790798655.5779166, "status": "ok", "ok": true, "valid": true, "correct": false, "predicted": "bad_push", "ordinal_ev": null, "probs": {"bad_push": 0.7518757352522394, "database_hardware": 0.10098383660000465, "upstream_provider": 0.14714042814775588}, "probs_as_returned": {"bad_push": 0.7518757352522394, "database_hardware": 0.10098383660000465, "upstream_provider": 0.14714042814775588}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.062460822984576225, "usage": {"input_tokens": 611, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "80f76503ea8e927c0692e4f0fdaaeb4006d98d3395e8c1bb5db3897ff06a6ce3", "runtime": null}
|
|
|
|
|
{"task_id": "hard-opus-b-probability-03", "family": "probability", "split": "public", "group": "hard-opus-b-probability-03", "ts": 1790798655.6709995, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "yes", "ordinal_ev": null, "probs": {"yes": 0.6798002499763626, "no": 0.32019975002363743}, "probs_as_returned": {"yes": 0.6798002499763626, "no": 0.32019975002363743}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.0827618139446713, "usage": {"input_tokens": 1327, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "c5d5d11d3c5dd2a269aa4f05b41b532520441ad65b699466cafd61ddefbcad5d", "runtime": null}
|
|
|
|
|
{"task_id": "hard-opus-b-probability-04", "family": "probability", "split": "public", "group": "hard-opus-b-probability-04", "ts": 1790798655.7427897, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "attended", "ordinal_ev": null, "probs": {"attended": 0.8908360355378411, "late_cancellation": 0.07712171561686927, "no_show": 0.03204224884528953}, "probs_as_returned": {"attended": 0.8908360355378411, "late_cancellation": 0.07712171561686927, "no_show": 0.03204224884528953}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.060617514012847096, "usage": {"input_tokens": 712, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "cd2ca2b513132da10e135e07a14d8cc268498019929da4aaee9ca710b7e08c7d", "runtime": null}
|
|
|
|
|
{"task_id": "hard-opus-b-probability-06", "family": "probability", "split": "public", "group": "hard-opus-b-probability-06", "ts": 1790798655.8295298, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "upheld", "ordinal_ev": null, "probs": {"modified": 0.13231015935842363, "overturned": 0.23270913097863707, "upheld": 0.6349807096629393}, "probs_as_returned": {"modified": 0.13231015935842363, "overturned": 0.23270913097863707, "upheld": 0.6349807096629393}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.0772057690192014, "usage": {"input_tokens": 1130, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "87159d8740c9adb062001b1f35759ca82e7146ffc180f06d171f50a2e27094d4", "runtime": null}
|
|
|
|
|
{"task_id": "hard-opus-b-tradeoff-01", "family": "tradeoff", "split": "public", "group": "hard-opus-b-tradeoff-01", "ts": 1790798655.9088092, "status": "ok", "ok": true, "valid": true, "correct": false, "predicted": "escalate_to_security", "ordinal_ev": null, "probs": {"escalate_to_engineering": 0.3134898075110609, "escalate_to_security": 0.6655546819611511, "page_oncall": 0.006021181075378121, "process_refund": 0.009946155239190027, "send_kb_article": 0.004988174213219846}, "probs_as_returned": {"escalate_to_engineering": 0.3134898075110609, "escalate_to_security": 0.6655546819611511, "page_oncall": 0.006021181075378121, "process_refund": 0.009946155239190027, "send_kb_article": 0.004988174213219846}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.06860842299647629, "usage": {"input_tokens": 957, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "6989402a2f53a48779755b4d2ab9b49cc8759cee1cc3a03e44aa47f8374d9964", "runtime": null}
|
|
|
|
|
{"task_id": "hard-opus-b-tradeoff-03", "family": "tradeoff", "split": "public", "group": "hard-opus-b-tradeoff-03", "ts": 1790798655.9837694, "status": "ok", "ok": true, "valid": true, "correct": false, "predicted": "order_a", "ordinal_ev": null, "probs": {"order_a": 0.6129149232266266, "order_b": 0.3484816687969538, "order_c": 0.023473188687705322, "order_d": 0.015130219288714327}, "probs_as_returned": {"order_a": 0.6129149232266266, "order_b": 0.3484816687969538, "order_c": 0.023473188687705322, "order_d": 0.015130219288714327}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.06490978802321479, "usage": {"input_tokens": 879, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "a530256a3e1ce656f580518a6e92fb36f7b5a5481bf381973f6854b78213866e", "runtime": null}
|
|
|
|
|
{"task_id": "hard-opus-b-tradeoff-06", "family": "tradeoff", "split": "public", "group": "hard-opus-b-tradeoff-06", "ts": 1790798656.0614529, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "yes", "ordinal_ev": null, "probs": {"yes": 0.844739173437523, "no": 0.15526082656247697}, "probs_as_returned": {"yes": 0.844739173437523, "no": 0.15526082656247697}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.06650745798833668, "usage": {"input_tokens": 905, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "19090abb3e919642460304e63fe95545d81d514f45af0986addcdd0696a66231", "runtime": null}
|
|
|
|
|
{"task_id": "hard-opus-b-tradeoff-07", "family": "tradeoff", "split": "public", "group": "hard-opus-b-tradeoff-07", "ts": 1790798656.1399064, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "p0_fix_24h", "ordinal_ev": null, "probs": {"out_of_scope": 0.008135371574581048, "p0_fix_24h": 0.7449709949864798, "p1_fix_7d": 0.1873751928949244, "p2_fix_30d": 0.05688855468489418, "p3_backlog": 0.0026298858591205228}, "probs_as_returned": {"out_of_scope": 0.008135371574581048, "p0_fix_24h": 0.7449709949864798, "p1_fix_7d": 0.1873751928949244, "p2_fix_30d": 0.05688855468489418, "p3_backlog": 0.0026298858591205228}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.06643087102565914, "usage": {"input_tokens": 836, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "ec58c67988b591fccccea4620461b0a90918e407ecf80d795f0d7679e0af8373", "runtime": null}
|
|
|
|
|
{"task_id": "hard-opus-b-tradeoff-08", "family": "tradeoff", "split": "public", "group": "hard-opus-b-tradeoff-08", "ts": 1790798656.2167604, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "yes", "ordinal_ev": null, "probs": {"yes": 0.8678561574454184, "no": 0.13214384255458156}, "probs_as_returned": {"yes": 0.8678561574454184, "no": 0.13214384255458156}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.0650076589663513, "usage": {"input_tokens": 718, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "5e1db8a4dd780932a55c1edda84c3de84b4bc90b91a0d314cff00ee17cafc680", "runtime": null}
|
|
|
|
|
{"task_id": "hard-opus-b-tradeoff-12", "family": "tradeoff", "split": "public", "group": "hard-opus-b-tradeoff-12", "ts": 1790798656.2887168, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "refund_now", "ordinal_ev": null, "probs": {"deny_refund": 0.0072570034281931855, "escalate_to_fraud_team": 0.004980548547941255, "offer_store_credit": 0.011258595089608286, "refund_now": 0.9682766780586276, "wait_for_inspection": 0.008227174875629762}, "probs_as_returned": {"deny_refund": 0.0072570034281931855, "escalate_to_fraud_team": 0.004980548547941255, "offer_store_credit": 0.011258595089608286, "refund_now": 0.9682766780586276, "wait_for_inspection": 0.008227174875629762}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.06139831501059234, "usage": {"input_tokens": 711, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "a7f565f7b493021dc5acfd541ece0007b7aec92237057bf157e5ef95270d462e", "runtime": null}
|
|
|
|
|
{"task_id": "hard-opus-c-long_policy-02", "family": "long_policy", "split": "public", "group": "hard-opus-c-long_policy-02", "ts": 1790798656.4895585, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "erase_but_retain_transaction_records", "ordinal_ev": null, "probs": {"erase_all": 0.05664948434336836, "erase_but_retain_transaction_records": 0.8954689046360063, "erase_marketing_only": 0.00714586913522651, "reject_unverified_request": 0.02353652032748053, "restrict_all_pending_legal_hold": 0.017199221557918292}, "probs_as_returned": {"erase_all": 0.05664948434336836, "erase_but_retain_transaction_records": 0.8954689046360063, "erase_marketing_only": 0.00714586913522651, "reject_unverified_request": 0.02353652032748053, "restrict_all_pending_legal_hold": 0.017199221557918292}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.18918431299971417, "usage": {"input_tokens": 3728, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "e5207cd4e5bfaf6a7c9a82594299a628880e96ca624ca58b720caf5d90786443", "runtime": null}
|
|
|
|
|
{"task_id": "hard-opus-c-long_policy-03", "family": "long_policy", "split": "public", "group": "hard-opus-c-long_policy-03", "ts": 1790798656.6891544, "status": "ok", "ok": true, "valid": true, "correct": false, "predicted": "eur_300", "ordinal_ev": null, "probs": {"eur_0": 0.01383331223422414, "eur_150": 0.2328238201782844, "eur_200": 0.2478986155873501, "eur_300": 0.31861107612832196, "eur_400": 0.17013510609182225, "eur_600": 0.016698069779997195}, "probs_as_returned": {"eur_0": 0.01383331223422414, "eur_150": 0.2328238201782844, "eur_200": 0.2478986155873501, "eur_300": 0.31861107612832196, "eur_400": 0.17013510609182225, "eur_600": 0.016698069779997195}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.18380610999884084, "usage": {"input_tokens": 3638, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "9c04bcea81681fefb11b63ff0bdcce1f0adb378fa44f9ac3f9991af3a2fa4aa8", "runtime": null}
|
|
|
|
|
{"task_id": "hard-opus-c-long_policy-04", "family": "long_policy", "split": "public", "group": "hard-opus-c-long_policy-04", "ts": 1790798656.8810284, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "yes", "ordinal_ev": null, "probs": {"yes": 0.9439168356016766, "no": 0.05608316439832339}, "probs_as_returned": {"yes": 0.9439168356016766, "no": 0.05608316439832339}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.1764982839813456, "usage": {"input_tokens": 3450, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "6bf5177150e1497491333ea7248907ff58bf3288947268d74bc8049ca20e2fb2", "runtime": null}
|
|
|
|
|
{"task_id": "hard-opus-c-long_policy-05", "family": "long_policy", "split": "public", "group": "hard-opus-c-long_policy-05", "ts": 1790798657.0704193, "status": "ok", "ok": true, "valid": true, "correct": false, "predicted": "2", "ordinal_ev": 1.8009979573655441, "probs": {"0": 0.10684458399102813, "1": 0.22683645296660385, "2": 0.4247953847281636, "3": 0.2415235783142044}, "probs_as_returned": {"0": 0.10684458399102813, "1": 0.22683645296660385, "2": 0.4247953847281636, "3": 0.2415235783142044}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.17454829899361357, "usage": {"input_tokens": 3385, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "f71b79acaf4fdd6fe203c273ffd1d11c8f37a25cffd9790bf48c33b3103dadb4", "runtime": null}
|
|
|
|
|
{"task_id": "hard-opus-c-long_policy-08", "family": "long_policy", "split": "public", "group": "hard-opus-c-long_policy-08", "ts": 1790798657.2627437, "status": "ok", "ok": true, "valid": true, "correct": false, "predicted": "2", "ordinal_ev": 1.886612524670372, "probs": {"0": 0.014822349797496677, "1": 0.19410266301948487, "2": 0.6807150998981681, "3": 0.11035988728485027}, "probs_as_returned": {"0": 0.014822349797496677, "1": 0.19410266301948487, "2": 0.6807150998981681, "3": 0.11035988728485027}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.17592920002061874, "usage": {"input_tokens": 3402, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "f3818740bd6600a1ab211046e2c57a5842aa7c534685e7f216aa3727901ebc61", "runtime": null}
|
|
|
|
|
{"task_id": "hard-opus-c-long_policy-10", "family": "long_policy", "split": "public", "group": "hard-opus-c-long_policy-10", "ts": 1790798657.4636235, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "credit_minus_restocking_fee", "ordinal_ev": null, "probs": {"credit_minus_restocking_fee": 0.8606962036243352, "full_credit": 0.04236513446101119, "reject_return": 0.07933695250396099, "repair_or_replace_only": 0.017601709410692636}, "probs_as_returned": {"credit_minus_restocking_fee": 0.8606962036243352, "full_credit": 0.04236513446101119, "reject_return": 0.07933695250396099, "repair_or_replace_only": 0.017601709410692636}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.18779821001226082, "usage": {"input_tokens": 3764, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "1f9ea7bc4f505d5d66ac450b44b3924cc4cde9c10311c633925d66ec8bef3e44", "runtime": null}
|
|
|
|
|
{"task_id": "hard-opus-c-long_policy-11", "family": "long_policy", "split": "public", "group": "hard-opus-c-long_policy-11", "ts": 1790798657.655003, "status": "ok", "ok": true, "valid": true, "correct": false, "predicted": "yes", "ordinal_ev": null, "probs": {"yes": 0.8940776460411956, "no": 0.10592235395880445}, "probs_as_returned": {"yes": 0.8940776460411956, "no": 0.10592235395880445}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.1780496829887852, "usage": {"input_tokens": 3528, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "460431d12f0a4651f82ccb00f0a6efafad641edc54766d7656927e1c3b65472c", "runtime": null}
|
|
|
|
|
{"task_id": "hard-opus-c-probability-03", "family": "probability", "split": "public", "group": "hard-opus-c-probability-03", "ts": 1790798657.7312965, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "kuznets_technik", "ordinal_ev": null, "probs": {"halvorsen_polymer": 0.10720891270072189, "kuznets_technik": 0.7982245521997403, "ortega_seal_works": 0.09456653509953773}, "probs_as_returned": {"halvorsen_polymer": 0.10720891270072189, "kuznets_technik": 0.7982245521997403, "ortega_seal_works": 0.09456653509953773}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.06501023500459269, "usage": {"input_tokens": 668, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "ad728e105decb6dfe3cdfee6f0651392b6199f7ca82cb6f9ea52978b4c34b4da", "runtime": null}
|
|
|
|
|
{"task_id": "hard-opus-c-temporal_numeric-02", "family": "temporal_numeric", "split": "public", "group": "hard-opus-c-temporal_numeric-02", "ts": 1790798657.817776, "status": "ok", "ok": true, "valid": true, "correct": false, "predicted": "no", "ordinal_ev": null, "probs": {"yes": 0.1724380672551571, "no": 0.8275619327448429}, "probs_as_returned": {"yes": 0.1724380672551571, "no": 0.8275619327448429}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.07449383498169482, "usage": {"input_tokens": 1053, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "c18a94bc6e81657e150dc2f23e79da41b2665e4ee1fe1b40dc7f7e0bb291992e", "runtime": null}
|
|
|
|
|
{"task_id": "hard-opus-c-temporal_numeric-03", "family": "temporal_numeric", "split": "public", "group": "hard-opus-c-temporal_numeric-03", "ts": 1790798657.8974347, "status": "ok", "ok": true, "valid": true, "correct": false, "predicted": "eur_617_00", "ordinal_ev": null, "probs": {"eur_617_00": 0.36635352271372007, "eur_688_00": 0.2514317984133709, "eur_692_00": 0.22178227377039253, "eur_693_90": 0.111227754246519, "eur_812_00": 0.04920465085599755}, "probs_as_returned": {"eur_617_00": 0.36635352271372007, "eur_688_00": 0.2514317984133709, "eur_692_00": 0.22178227377039253, "eur_693_90": 0.111227754246519, "eur_812_00": 0.04920465085599755}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.0676459270180203, "usage": {"input_tokens": 986, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "f1beb2d2222b8c9dc458b653c6c7c4f007dc8727c5826850ee1d20c431aee419", "runtime": null}
|
|
|
|
|
{"task_id": "hard-opus-c-temporal_numeric-04", "family": "temporal_numeric", "split": "public", "group": "hard-opus-c-temporal_numeric-04", "ts": 1790798657.9769113, "status": "ok", "ok": true, "valid": true, "correct": false, "predicted": "usd_2303_01", "ordinal_ev": null, "probs": {"usd_2222_50": 0.014913710681025665, "usd_2303_01": 0.34349499154165725, "usd_2303_33": 0.3226069482266983, "usd_2335_00": 0.2079442332558462, "usd_2340_00": 0.11104011629477252}, "probs_as_returned": {"usd_2222_50": 0.014913710681025665, "usd_2303_01": 0.34349499154165725, "usd_2303_33": 0.3226069482266983, "usd_2335_00": 0.2079442332558462, "usd_2340_00": 0.11104011629477252}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.06735935702454299, "usage": {"input_tokens": 899, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "ffb53afd1475aaa7b7c60daca719c7990d39177369198b2b01a85463109050a7", "runtime": null}
|
|
|
|
|
{"task_id": "hard-opus-c-temporal_numeric-06", "family": "temporal_numeric", "split": "public", "group": "hard-opus-c-temporal_numeric-06", "ts": 1790798658.0611448, "status": "ok", "ok": true, "valid": true, "correct": false, "predicted": "sep_16_taxi", "ordinal_ev": null, "probs": {"none_declined": 0.02623440752459831, "sep_15_office_chair": 0.25104537458089066, "sep_16_taxi": 0.5674913765540806, "sep_17_parking": 0.04614147757294348, "sep_18_book_set": 0.08115433880928592, "sep_21_client_dinner": 0.027933024958201016}, "probs_as_returned": {"none_declined": 0.02623440752459831, "sep_15_office_chair": 0.25104537458089066, "sep_16_taxi": 0.5674913765540806, "sep_17_parking": 0.04614147757294348, "sep_18_book_set": 0.08115433880928592, "sep_21_client_dinner": 0.027933024958201016}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.07365977100562304, "usage": {"input_tokens": 1102, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "dc9982fb0ecfb6e46997f91ae21adc4e643007dc7625e82b51f03dc00af25efa", "runtime": null}
|
|
|
|
|
{"task_id": "hard-opus-c-temporal_numeric-08", "family": "temporal_numeric", "split": "public", "group": "hard-opus-c-temporal_numeric-08", "ts": 1790798658.1450608, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "eur_498_81", "ordinal_ev": null, "probs": {"eur_497_40": 0.22970119120589697, "eur_498_81": 0.37943445912969975, "eur_506_06": 0.13905597950085433, "eur_513_69": 0.19029314129726177, "eur_532_01": 0.06151522886628714}, "probs_as_returned": {"eur_497_40": 0.22970119120589697, "eur_498_81": 0.37943445912969975, "eur_506_06": 0.13905597950085433, "eur_513_69": 0.19029314129726177, "eur_532_01": 0.06151522886628714}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.07407018798403442, "usage": {"input_tokens": 1105, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "62d06b020ad4c6dad356379f0a97690689aad0f4b65756c546a2276e8a3436ea", "runtime": null}
|
|
|
|
|
{"task_id": "hard-opus-c-temporal_numeric-12", "family": "temporal_numeric", "split": "public", "group": "hard-opus-c-temporal_numeric-12", "ts": 1790798658.2242763, "status": "ok", "ok": true, "valid": true, "correct": false, "predicted": "expired_24_month_term", "ordinal_ev": null, "probs": {"covered": 0.1309008006401481, "expired_24_month_term": 0.488790641617104, "expired_30_month_cap": 0.3803085577427478}, "probs_as_returned": {"covered": 0.1309008006401481, "expired_24_month_term": 0.488790641617104, "expired_30_month_cap": 0.3803085577427478}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.0674421259900555, "usage": {"input_tokens": 935, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "8e41724cb0c91441222a35332277fc384ee2ee543650f01a335937fd85f6c2de", "runtime": null}
|
|
|
|
|
{"task_id": "hard-sol-a-adversarial-01", "family": "adversarial", "split": "public", "group": "hard-sol-a-adversarial-01", "ts": 1790798658.2929623, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "deny_missing_approval", "ordinal_ev": null, "probs": {"deny_inactive_user": 0.013568707364640402, "deny_missing_approval": 0.8527472004718343, "grant_access": 0.03265819804374573, "grant_owner_exception": 0.10102589411977958}, "probs_as_returned": {"deny_inactive_user": 0.013568707364640402, "deny_missing_approval": 0.8527472004718343, "grant_access": 0.03265819804374573, "grant_owner_exception": 0.10102589411977958}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05771850096061826, "usage": {"input_tokens": 390, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "4a22266fdb65ee882f90a2f4199d377371ace659675d4b4414d11a12118553be", "runtime": null}
|
|
|
|
|
{"task_id": "hard-sol-a-adversarial-06", "family": "adversarial", "split": "public", "group": "hard-sol-a-adversarial-06", "ts": 1790798658.3585253, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "no", "ordinal_ev": null, "probs": {"yes": 0.016659759016074603, "no": 0.9833402409839254}, "probs_as_returned": {"yes": 0.016659759016074603, "no": 0.9833402409839254}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05558245204156265, "usage": {"input_tokens": 350, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "453eedb759be4689c30c14ae95e6059d088ff613b7d83728cceb8080b05f92bb", "runtime": null}
|
|
|
|
|
{"task_id": "hard-sol-a-adversarial-07", "family": "adversarial", "split": "public", "group": "hard-sol-a-adversarial-07", "ts": 1790798658.4249399, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "retain_until_2031", "ordinal_ev": null, "probs": {"delete_now": 0.010441518332080891, "needs_signature_review": 0.004918167733746614, "retain_indefinitely": 0.02849120141460286, "retain_until_2031": 0.9561491125195697}, "probs_as_returned": {"delete_now": 0.010441518332080891, "needs_signature_review": 0.004918167733746614, "retain_indefinitely": 0.02849120141460286, "retain_until_2031": 0.9561491125195697}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.056003466015681624, "usage": {"input_tokens": 406, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "23ae50b983e765fc69a1445a939c170b4e947af963c6bfa988fafc8901255811", "runtime": null}
|
|
|
|
|
{"task_id": "hard-sol-a-adversarial-08", "family": "adversarial", "split": "public", "group": "hard-sol-a-adversarial-08", "ts": 1790798658.4910605, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "yes", "ordinal_ev": null, "probs": {"yes": 0.9502009729447547, "no": 0.049799027055245304}, "probs_as_returned": {"yes": 0.9502009729447547, "no": 0.049799027055245304}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05539108801167458, "usage": {"input_tokens": 327, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "a2680bd447dec9f52cf860d666a9dc94c8f3d9ac2ae95203f0b7706047f5a1a0", "runtime": null}
|
|
|
|
|
{"task_id": "hard-sol-a-adversarial-09", "family": "adversarial", "split": "public", "group": "hard-sol-a-adversarial-09", "ts": 1790798658.5559196, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "2", "ordinal_ev": 1.8962367066579777, "probs": {"0": 0.012249937955791055, "1": 0.09711242419678795, "2": 0.8727886310810733, "3": 0.01784900676634773}, "probs_as_returned": {"0": 0.012249937955791055, "1": 0.09711242419678795, "2": 0.8727886310810733, "3": 0.01784900676634773}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05558434099657461, "usage": {"input_tokens": 344, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "c2e694137068b840cbe4e2177c4161683309fe409b4d0a8c389812436010fd19", "runtime": null}
|
|
|
|
|
{"task_id": "hard-sol-a-adversarial-11", "family": "adversarial", "split": "public", "group": "hard-sol-a-adversarial-11", "ts": 1790798658.619973, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "standard_research", "ordinal_ev": null, "probs": {"ethics_review": 0.023754425327906448, "major_grants": 0.009869402226303762, "manual_hold": 0.004100502827029603, "standard_research": 0.9622756696187603}, "probs_as_returned": {"ethics_review": 0.023754425327906448, "major_grants": 0.009869402226303762, "manual_hold": 0.004100502827029603, "standard_research": 0.9622756696187603}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05541436199564487, "usage": {"input_tokens": 411, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "aac0aa2f8ad70d703a8a8a466a7e18cb4852d1fbf6c855811b7162522834ac91", "runtime": null}
|
|
|
|
|
{"task_id": "hard-sol-a-multi_hop-01", "family": "multi_hop", "split": "public", "group": "hard-sol-a-multi_hop-01", "ts": 1790798658.7791986, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "accept_s2_dusk", "ordinal_ev": null, "probs": {"accept_s2_dusk": 0.8820299897169496, "reject_cutoff": 0.04077512878367174, "reject_tier": 0.033779658694117705, "reroute_s3": 0.04341522280526092}, "probs_as_returned": {"accept_s2_dusk": 0.8820299897169496, "reject_cutoff": 0.04077512878367174, "reject_tier": 0.033779658694117705, "reroute_s3": 0.04341522280526092}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.14691848697839305, "usage": {"input_tokens": 2819, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "dd32088cf49c4f1d5e02ed70308e3d42b6b0f803aee2a2aefd6753fcb5dd65cc", "runtime": null}
|
|
|
|
|
{"task_id": "hard-sol-a-multi_hop-02", "family": "multi_hop", "split": "public", "group": "hard-sol-a-multi_hop-02", "ts": 1790798658.9406123, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "security_primary", "ordinal_ev": null, "probs": {"executive_bridge": 0.019116772677897714, "heron_q2": 0.08092609404342527, "insufficient_information": 0.12554962605057535, "security_primary": 0.7744075072281016}, "probs_as_returned": {"executive_bridge": 0.019116772677897714, "heron_q2": 0.08092609404342527, "insufficient_information": 0.12554962605057535, "security_primary": 0.7744075072281016}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.1479988689534366, "usage": {"input_tokens": 2867, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "70d56f36111ceae4acafa02aa2990832ab807b13a6051b52eace32f858eec06b", "runtime": null}
|
|
|
|
|
{"task_id": "hard-sol-a-multi_hop-05", "family": "multi_hop", "split": "public", "group": "hard-sol-a-multi_hop-05", "ts": 1790798659.0951865, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "require_director", "ordinal_ev": null, "probs": {"pay_manager_approved": 0.2549478953776852, "reject_category": 0.034241851845298925, "require_director": 0.6956624298246201, "require_finance_board": 0.015147822952395761}, "probs_as_returned": {"pay_manager_approved": 0.2549478953776852, "reject_category": 0.034241851845298925, "require_director": 0.6956624298246201, "require_finance_board": 0.015147822952395761}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.1402906560106203, "usage": {"input_tokens": 2779, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "5ce3fcfdbf679a64e33907d38551027005925e5d44a4815e1f48a9dab40a47e2", "runtime": null}
|
|
|
|
|
{"task_id": "hard-sol-a-multi_hop-07", "family": "multi_hop", "split": "public", "group": "hard-sol-a-multi_hop-07", "ts": 1790798659.2482078, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "admit", "ordinal_ev": null, "probs": {"admit": 0.8016965785406263, "deny_prerequisite": 0.11464694915891029, "deny_score": 0.061220315486799355, "manual_equivalency": 0.02243615681366412}, "probs_as_returned": {"admit": 0.8016965785406263, "deny_prerequisite": 0.11464694915891029, "deny_score": 0.061220315486799355, "manual_equivalency": 0.02243615681366412}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.1405552140204236, "usage": {"input_tokens": 2760, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "f1892e946bd74846c552758d421e7b35892c20f5824c32a83ebf35b4c53b6818", "runtime": null}
|
|
|
|
|
{"task_id": "hard-sol-a-multi_hop-08", "family": "multi_hop", "split": "public", "group": "hard-sol-a-multi_hop-08", "ts": 1790798659.4019012, "status": "ok", "ok": true, "valid": true, "correct": false, "predicted": "local_maintenance", "ordinal_ev": null, "probs": {"central_engineering": 0.2039312595652488, "insufficient_log": 0.025724259265304274, "local_maintenance": 0.7614902860659044, "safety_shutdown": 0.00885419510354259}, "probs_as_returned": {"central_engineering": 0.2039312595652488, "insufficient_log": 0.025724259265304274, "local_maintenance": 0.7614902860659044, "safety_shutdown": 0.00885419510354259}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.13950889802072197, "usage": {"input_tokens": 2730, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "540489cd20fd163fb294f960169484c5533c5e33c40cfd9313be450f6f913fdd", "runtime": null}
|
|
|
|
|
{"task_id": "hard-sol-a-multi_hop-09", "family": "multi_hop", "split": "public", "group": "hard-sol-a-multi_hop-09", "ts": 1790798659.5567603, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "require_steward", "ordinal_ev": null, "probs": {"confirm_l3": 0.06689419587938847, "reject_capacity": 0.03803366795607197, "require_steward": 0.8759975739130693, "switch_l4": 0.019074562251470206}, "probs_as_returned": {"confirm_l3": 0.06689419587938847, "reject_capacity": 0.03803366795607197, "require_steward": 0.8759975739130693, "switch_l4": 0.019074562251470206}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.14082592504564673, "usage": {"input_tokens": 2744, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "24a8df8e819e40004bf623867fc1ef3005b4c895e3dc806d2b41dc6ef7fefe6d", "runtime": null}
|
|
|
|
|
{"task_id": "hard-sol-a-multi_hop-10", "family": "multi_hop", "split": "public", "group": "hard-sol-a-multi_hop-10", "ts": 1790798659.7110531, "status": "ok", "ok": true, "valid": true, "correct": false, "predicted": "reduce_to_30_days", "ordinal_ev": null, "probs": {"approve_45_days": 0.2266260914546683, "deny_sensitive": 0.013465071955275236, "needs_field_review": 0.013465071955275236, "reduce_to_30_days": 0.7464437646347811}, "probs_as_returned": {"approve_45_days": 0.2266260914546683, "deny_sensitive": 0.013465071955275236, "needs_field_review": 0.013465071955275236, "reduce_to_30_days": 0.7464437646347811}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.14173494797432795, "usage": {"input_tokens": 2808, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "a9176be01ee50a8e72c8d6c29ea6eaa267d4f0002176414eaffe147bdea595ac", "runtime": null}
|
|
|
|
|
{"task_id": "hard-sol-a-multi_hop-12", "family": "multi_hop", "split": "public", "group": "hard-sol-a-multi_hop-12", "ts": 1790798659.8627214, "status": "ok", "ok": true, "valid": true, "correct": false, "predicted": "covered_recurrence", "ordinal_ev": null, "probs": {"covered_recurrence": 0.5488178934874424, "expired": 0.01853987381447562, "needs_authentication": 0.4270133837934193, "wrong_issue_class": 0.0056288489046627905}, "probs_as_returned": {"covered_recurrence": 0.5488178934874424, "expired": 0.01853987381447562, "needs_authentication": 0.4270133837934193, "wrong_issue_class": 0.0056288489046627905}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.13972810801351443, "usage": {"input_tokens": 2755, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "aa0d6c687b7e3f74acc21488e8962af8e786a885140643063e1ab2acd994bbb3", "runtime": null}
|
|
|
|
|
{"task_id": "hard-sol-a-trap-02", "family": "trap", "split": "public", "group": "hard-sol-a-trap-02", "ts": 1790798659.9328625, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "no", "ordinal_ev": null, "probs": {"yes": 0.03075154512433679, "no": 0.9692484548756632}, "probs_as_returned": {"yes": 0.03075154512433679, "no": 0.9692484548756632}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05799433699576184, "usage": {"input_tokens": 401, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "56bd867301a41e828de32240324d083016f3f3ed008d1c14609bb88a6692da85", "runtime": null}
|
|
|
|
|
{"task_id": "hard-sol-a-trap-04", "family": "trap", "split": "public", "group": "hard-sol-a-trap-04", "ts": 1790798659.999397, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "no", "ordinal_ev": null, "probs": {"yes": 0.059498364613396776, "no": 0.9405016353866033}, "probs_as_returned": {"yes": 0.059498364613396776, "no": 0.9405016353866033}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05570444400655106, "usage": {"input_tokens": 307, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "a6cd798c36dcdbe276423c2e28dc57b18dce790acf12612fd1f6f566494a2d83", "runtime": null}
|
|
|
|
|
{"task_id": "hard-sol-a-trap-05", "family": "trap", "split": "public", "group": "hard-sol-a-trap-05", "ts": 1790798660.0678842, "status": "ok", "ok": true, "valid": true, "correct": false, "predicted": "1", "ordinal_ev": 0.8643000081318148, "probs": {"0": 0.34057212036202084, "1": 0.4660607766073019, "2": 0.1818620775675192, "3": 0.01150502546315819}, "probs_as_returned": {"0": 0.34057212036202084, "1": 0.4660607766073019, "2": 0.1818620775675192, "3": 0.01150502546315819}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05672413797583431, "usage": {"input_tokens": 454, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "95cf196902b09e503e2a1b1d163f33e7c1907920fc3f16fbe0b47a121a23b360", "runtime": null}
|
|
|
|
|
{"task_id": "hard-sol-a-trap-06", "family": "trap", "split": "public", "group": "hard-sol-a-trap-06", "ts": 1790798660.1352375, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "keep_open_unresolved", "ordinal_ev": null, "probs": {"await_internal_metrics": 0.008337830351487158, "close_agent_verified": 0.0025314294996148625, "close_confirmed": 0.007830803388441922, "keep_open_unresolved": 0.981299936760456}, "probs_as_returned": {"await_internal_metrics": 0.008337830351487158, "close_agent_verified": 0.0025314294996148625, "close_confirmed": 0.007830803388441922, "keep_open_unresolved": 0.981299936760456}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.056547317013610154, "usage": {"input_tokens": 459, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "c5e1d48ab209ec264362f87dab10b9bcf494195351da2e1e347f0000057c836e", "runtime": null}
|
|
|
|
|
{"task_id": "hard-sol-a-trap-08", "family": "trap", "split": "public", "group": "hard-sol-a-trap-08", "ts": 1790798660.2017713, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "late", "ordinal_ev": null, "probs": {"canceled": 0.0052844814699961285, "indeterminate": 0.00282185985242437, "late": 0.9648903851080965, "on_time": 0.027003273569482986}, "probs_as_returned": {"canceled": 0.0052844814699961285, "indeterminate": 0.00282185985242437, "late": 0.9648903851080965, "on_time": 0.027003273569482986}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05549893400166184, "usage": {"input_tokens": 386, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "0a929d93af499d0a0d9acc1e647407e149338733020fc8f103615b15026ac8a9", "runtime": null}
|
|
|
|
|
{"task_id": "hard-sol-a-trap-10", "family": "trap", "split": "public", "group": "hard-sol-a-trap-10", "ts": 1790798660.2690434, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "blocked_second_review", "ordinal_ev": null, "probs": {"blocked_failed_test": 0.014370727476242724, "blocked_second_review": 0.9616283560317681, "ready_one_review": 0.00869971844133038, "ready_two_reviews": 0.015301198050658662}, "probs_as_returned": {"blocked_failed_test": 0.014370727476242724, "blocked_second_review": 0.9616283560317681, "ready_one_review": 0.00869971844133038, "ready_two_reviews": 0.015301198050658662}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05579993303399533, "usage": {"input_tokens": 312, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "00882d2a9b2dd45152936cee243b2e8eb1548d5188794ac6fc52df6977b488b1", "runtime": null}
|
|
|
|
|
{"task_id": "hard-sol-a-trap-13", "family": "trap", "split": "public", "group": "hard-sol-a-trap-13", "ts": 1790798660.3359685, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "no", "ordinal_ev": null, "probs": {"yes": 0.022659190258890113, "no": 0.9773408097411099}, "probs_as_returned": {"yes": 0.022659190258890113, "no": 0.9773408097411099}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05513175204396248, "usage": {"input_tokens": 315, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "d8d3c431b2b5a04ddad88d27f912ebb2ff0dfd293c17d13c27df364284580ebf", "runtime": null}
|
|
|
|
|
{"task_id": "hard-sol-a-trap-15", "family": "trap", "split": "public", "group": "hard-sol-a-trap-15", "ts": 1790798660.4028685, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "no", "ordinal_ev": null, "probs": {"yes": 0.14720923592665844, "no": 0.8527907640733415}, "probs_as_returned": {"yes": 0.14720923592665844, "no": 0.8527907640733415}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05554864602163434, "usage": {"input_tokens": 417, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "be15699dd9f36f612e358364ae3a6b272ebafc28cf9d76273540b1203961afae", "runtime": null}
|
|
|
|
|
{"task_id": "hard-sol-b-judge_hard-01", "family": "judge_hard", "split": "public", "group": "hard-sol-b-judge_hard-01", "ts": 1790798660.469689, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "yes", "ordinal_ev": null, "probs": {"yes": 0.8879876242264044, "no": 0.11201237577359557}, "probs_as_returned": {"yes": 0.8879876242264044, "no": 0.11201237577359557}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.055394411960151047, "usage": {"input_tokens": 402, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "57e1256bd6085b0a28b836a5fdb32445259d50065620b768c1e4237e84523371", "runtime": null}
|
|
|
|
|
{"task_id": "hard-sol-b-judge_hard-02", "family": "judge_hard", "split": "public", "group": "hard-sol-b-judge_hard-02", "ts": 1790798660.5359774, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "no", "ordinal_ev": null, "probs": {"yes": 0.2681939143399331, "no": 0.7318060856600669}, "probs_as_returned": {"yes": 0.2681939143399331, "no": 0.7318060856600669}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.055112886999268085, "usage": {"input_tokens": 326, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "be99ed3d024952976fc87012e9c24fd8e92f600e71eb69d718e708737dcdc8ea", "runtime": null}
|
|
|
|
|
{"task_id": "hard-sol-b-judge_hard-05", "family": "judge_hard", "split": "public", "group": "hard-sol-b-judge_hard-05", "ts": 1790798660.6021655, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "yes", "ordinal_ev": null, "probs": {"yes": 0.8363317223730603, "no": 0.1636682776269397}, "probs_as_returned": {"yes": 0.8363317223730603, "no": 0.1636682776269397}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05494544899556786, "usage": {"input_tokens": 346, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "4ce913211d113977d207c44b0b606ab88658839e08e1c85432c1ce87ad61a421", "runtime": null}
|
|
|
|
|
{"task_id": "hard-sol-b-judge_hard-08", "family": "judge_hard", "split": "public", "group": "hard-sol-b-judge_hard-08", "ts": 1790798660.669122, "status": "ok", "ok": true, "valid": true, "correct": false, "predicted": "yes", "ordinal_ev": null, "probs": {"yes": 0.8815938286018441, "no": 0.1184061713981559}, "probs_as_returned": {"yes": 0.8815938286018441, "no": 0.1184061713981559}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05521763500291854, "usage": {"input_tokens": 328, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "429b47f7fa48e412eaf1d1f4c048cf4cf8db44f1d8db9a4a5352f1b1475b52dc", "runtime": null}
|
|
|
|
|
{"task_id": "hard-sol-b-judge_hard-10", "family": "judge_hard", "split": "public", "group": "hard-sol-b-judge_hard-10", "ts": 1790798660.7347963, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "no", "ordinal_ev": null, "probs": {"yes": 0.3340072352673295, "no": 0.6659927647326704}, "probs_as_returned": {"yes": 0.3340072352673295, "no": 0.6659927647326704}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05488001502817497, "usage": {"input_tokens": 347, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "afd9f18d0327be04981b0c6b17623a33bfa95f32bba99e5f8b652e30d8895b83", "runtime": null}
|
|
|
|
|
{"task_id": "hard-sol-b-judge_hard-14", "family": "judge_hard", "split": "public", "group": "hard-sol-b-judge_hard-14", "ts": 1790798660.8017747, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "no", "ordinal_ev": null, "probs": {"yes": 0.011493812770397228, "no": 0.9885061872296028}, "probs_as_returned": {"yes": 0.011493812770397228, "no": 0.9885061872296028}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05558282503625378, "usage": {"input_tokens": 364, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "da6419543d5530e54524f8e88349b6fe2fbd0a008a11b22b45704298e31b3ac0", "runtime": null}
|
|
|
|
|
{"task_id": "hard-sol-b-judge_hard-15", "family": "judge_hard", "split": "public", "group": "hard-sol-b-judge_hard-15", "ts": 1790798660.8685966, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "yes", "ordinal_ev": null, "probs": {"yes": 0.9405016353866033, "no": 0.05949836461339675}, "probs_as_returned": {"yes": 0.9405016353866033, "no": 0.05949836461339675}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.055451991967856884, "usage": {"input_tokens": 320, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "5f944906307fab4c79ede852b15fc8657d69a02105b328d183aa4e619ef050a2", "runtime": null}
|
|
|
|
|
{"task_id": "hard-sol-b-judge_hard-18", "family": "judge_hard", "split": "public", "group": "hard-sol-b-judge_hard-18", "ts": 1790798660.9340646, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "no", "ordinal_ev": null, "probs": {"yes": 0.016659759016074603, "no": 0.9833402409839254}, "probs_as_returned": {"yes": 0.016659759016074603, "no": 0.9833402409839254}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05452302796766162, "usage": {"input_tokens": 288, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "150cbbe7167371da16d3c7ee2c020a4f6f812fc8917b0737aae74f8e87cb97cf", "runtime": null}
|
|
|
|
|
{"task_id": "hard-sol-b-long_policy-01", "family": "long_policy", "split": "public", "group": "hard-sol-b-long_policy-01", "ts": 1790798661.0987616, "status": "ok", "ok": true, "valid": true, "correct": false, "predicted": "approve_lodging_only", "ordinal_ev": null, "probs": {"approve_all": 0.08909463191094494, "approve_lodging_only": 0.706305265580735, "approve_meals_only": 0.14717197021020476, "reject_entire_claim": 0.05742813229811534}, "probs_as_returned": {"approve_all": 0.08909463191094494, "approve_lodging_only": 0.706305265580735, "approve_meals_only": 0.14717197021020476, "reject_entire_claim": 0.05742813229811534}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.15180334902834147, "usage": {"input_tokens": 2866, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "22da906b19126b73aa64d097cb5c42be9a154c907b1beeb79311ea0f29a2bb79", "runtime": null}
|
|
|
|
|
{"task_id": "hard-sol-b-long_policy-02", "family": "long_policy", "split": "public", "group": "hard-sol-b-long_policy-02", "ts": 1790798661.2559662, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "deny_current_export", "ordinal_ev": null, "probs": {"analytics_owner_only": 0.012159429361438828, "deny_current_export": 0.8663400458018994, "privacy_and_security": 0.10263625163294894, "privacy_only": 0.018864273203712912}, "probs_as_returned": {"analytics_owner_only": 0.012159429361438828, "deny_current_export": 0.8663400458018994, "privacy_and_security": 0.10263625163294894, "privacy_only": 0.018864273203712912}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.14383464498678222, "usage": {"input_tokens": 2716, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "9bd406d91ea8483105c85d701405bbf32be11c9bce7750f8017616ba3de241fd", "runtime": null}
|
|
|
|
|
{"task_id": "hard-sol-b-long_policy-05", "family": "long_policy", "split": "public", "group": "hard-sol-b-long_policy-05", "ts": 1790798661.4099793, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "delete_profile_omar_april_and_table", "ordinal_ev": null, "probs": {"delete_everything": 0.021894364677177067, "delete_nothing": 0.0233119742695315, "delete_only_profile": 0.34608827612402576, "delete_profile_omar_april_and_table": 0.6087053849292656}, "probs_as_returned": {"delete_everything": 0.021894364677177067, "delete_nothing": 0.0233119742695315, "delete_only_profile": 0.34608827612402576, "delete_profile_omar_april_and_table": 0.6087053849292656}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.1424006099696271, "usage": {"input_tokens": 2677, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "eef79a26b6ba1b7b0d619387d6a65a78c2149599f3847f809564d4004e7cf719", "runtime": null}
|
|
|
|
|
{"task_id": "hard-sol-b-long_policy-06", "family": "long_policy", "split": "public", "group": "hard-sol-b-long_policy-06", "ts": 1790798661.5706367, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "east_ward", "ordinal_ev": null, "probs": {"east_ward": 0.3411456641180011, "harbor_neighbors": 0.3009168221241823, "no_award": 0.016791849639815445, "river_arts": 0.3411456641180011}, "probs_as_returned": {"east_ward": 0.3411456641180011, "harbor_neighbors": 0.3009168221241823, "no_award": 0.016791849639815445, "river_arts": 0.3411456641180011}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.14596972498111427, "usage": {"input_tokens": 2760, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "a3d8e47cef61255be435ced9e8020aa3df825e9a46b9bc2735943568da280d26", "runtime": null}
|
|
|
|
|
{"task_id": "hard-sol-b-routing_hard-01", "family": "routing_hard", "split": "public", "group": "hard-sol-b-routing_hard-01", "ts": 1790798661.6408315, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "office_file_repair", "ordinal_ev": null, "probs": {"data_pipeline": 0.002432868028110054, "desktop_support": 0.003774378037715521, "finance_review": 0.004278965637903766, "office_file_repair": 0.9430929283602817, "spreadsheet_formula": 0.04642085993598908}, "probs_as_returned": {"data_pipeline": 0.002432868028110054, "desktop_support": 0.003774378037715521, "finance_review": 0.004278965637903766, "office_file_repair": 0.9430929283602817, "spreadsheet_formula": 0.04642085993598908}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.0577911640284583, "usage": {"input_tokens": 440, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "8420be412cf705cd5014fa62263fbc78c3d1f95ff9d5fde51cfbc31a18924dcd", "runtime": null}
|
|
|
|
|
{"task_id": "hard-sol-b-routing_hard-02", "family": "routing_hard", "split": "public", "group": "hard-sol-b-routing_hard-02", "ts": 1790798661.708583, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "ledger_reconciliation", "ordinal_ev": null, "probs": {"customer_support": 0.024586117348690935, "fraud_review": 0.0015553761372732856, "ledger_reconciliation": 0.9354018336737445, "mobile_app": 0.03364522339881921, "payment_disputes": 0.004811449441472035}, "probs_as_returned": {"customer_support": 0.024586117348690935, "fraud_review": 0.0015553761372732856, "ledger_reconciliation": 0.9354018336737445, "mobile_app": 0.03364522339881921, "payment_disputes": 0.004811449441472035}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.055701024015434086, "usage": {"input_tokens": 423, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "c7fa98909abd01abe2bbb910ff86ddeb0546227ed9f8f26c2040fc2c0f7f9e9d", "runtime": null}
|
|
|
|
|
{"task_id": "hard-sol-b-routing_hard-03", "family": "routing_hard", "split": "public", "group": "hard-sol-b-routing_hard-03", "ts": 1790798661.7760708, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "network_dns", "ordinal_ev": null, "probs": {"api_platform": 0.004842894208676956, "authoritative_dns": 0.005156460174491347, "endpoint_devices": 0.04634319529093982, "network_dns": 0.9415150632539939, "tls_certificates": 0.002142387071897831}, "probs_as_returned": {"api_platform": 0.004842894208676956, "authoritative_dns": 0.005156460174491347, "endpoint_devices": 0.04634319529093982, "network_dns": 0.9415150632539939, "tls_certificates": 0.002142387071897831}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05628473998513073, "usage": {"input_tokens": 421, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "9a908dc255c6cab623de43d90848fd8db2b4617b2cac371329370e41101111c4", "runtime": null}
|
|
|
|
|
{"task_id": "hard-sol-b-routing_hard-07", "family": "routing_hard", "split": "public", "group": "hard-sol-b-routing_hard-07", "ts": 1790798661.8419044, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "release_notarization", "ordinal_ev": null, "probs": {"ci_infrastructure": 0.0026358552072950053, "code_signing": 0.03044686823684439, "endpoint_security": 0.0026358552072950053, "macos_runtime": 0.004635982743818916, "release_notarization": 0.9596454386047467}, "probs_as_returned": {"ci_infrastructure": 0.0026358552072950053, "code_signing": 0.03044686823684439, "endpoint_security": 0.0026358552072950053, "macos_runtime": 0.004635982743818916, "release_notarization": 0.9596454386047467}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.0557621429907158, "usage": {"input_tokens": 404, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "866e250994138105e289bf37092f857633b8d3af56b4fcc3fe6cec2b977f7346", "runtime": null}
|
|
|
|
|
{"task_id": "hard-sol-b-routing_hard-09", "family": "routing_hard", "split": "public", "group": "hard-sol-b-routing_hard-09", "ts": 1790798661.9104817, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "source_access", "ordinal_ev": null, "probs": {"git_client": 0.020297759877090524, "identity_login": 0.006561567668597966, "repository_admin": 0.03352908025315896, "source_access": 0.9321728248733867, "vpn_network": 0.007438767327765931}, "probs_as_returned": {"git_client": 0.020297759877090524, "identity_login": 0.006561567668597966, "repository_admin": 0.03352908025315896, "source_access": 0.9321728248733867, "vpn_network": 0.007438767327765931}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05577813199488446, "usage": {"input_tokens": 410, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "5836c7a3a663636e09089f0735e7b86a21bde65572c6412d7d1ee3022af65f0b", "runtime": null}
|
|
|
|
|
{"task_id": "hard-sol-b-temporal_numeric-01", "family": "temporal_numeric", "split": "public", "group": "hard-sol-b-temporal_numeric-01", "ts": 1790798661.9784958, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "late_by_under_2h", "ordinal_ev": null, "probs": {"before_open": 0.07619692419201703, "late_by_2h_or_more": 0.2672214674340832, "late_by_under_2h": 0.38936014093981663, "within_window": 0.2672214674340832}, "probs_as_returned": {"before_open": 0.07619692419201703, "late_by_2h_or_more": 0.2672214674340832, "late_by_under_2h": 0.38936014093981663, "within_window": 0.2672214674340832}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.055911089992150664, "usage": {"input_tokens": 402, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "526d531a33c1650357fdc96427dff1c80d0428a43b135b1e8db09aad18cc8b60", "runtime": null}
|
|
|
|
|
{"task_id": "hard-sol-b-temporal_numeric-02", "family": "temporal_numeric", "split": "public", "group": "hard-sol-b-temporal_numeric-02", "ts": 1790798662.0458176, "status": "ok", "ok": true, "valid": true, "correct": false, "predicted": "under_100gb_below", "ordinal_ev": null, "probs": {"at_least_100gb_below": 0.2777216041744788, "exactly_equal": 0.20294399073523287, "over_limit": 0.1392823299139878, "under_100gb_below": 0.3800520751763005}, "probs_as_returned": {"at_least_100gb_below": 0.2777216041744788, "exactly_equal": 0.20294399073523287, "over_limit": 0.1392823299139878, "under_100gb_below": 0.3800520751763005}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05532720097107813, "usage": {"input_tokens": 415, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "9607ba5216aff84f705cca151fa0485f03c11567005227f05bddf16208919e54", "runtime": null}
|
|
|
|
|
{"task_id": "hard-sol-b-temporal_numeric-03", "family": "temporal_numeric", "split": "public", "group": "hard-sol-b-temporal_numeric-03", "ts": 1790798662.1156037, "status": "ok", "ok": true, "valid": true, "correct": false, "predicted": "12_credits", "ordinal_ev": null, "probs": {"12_credits": 0.38418415861441135, "15_credits": 0.11664127258300278, "6_credits": 0.21843347437078164, "9_credits": 0.28074109443180434}, "probs_as_returned": {"12_credits": 0.38418415861441135, "15_credits": 0.11664127258300278, "6_credits": 0.21843347437078164, "9_credits": 0.28074109443180434}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05616778996773064, "usage": {"input_tokens": 354, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "e9ca3868c06b1777151c868dd2c61563613252b7385ab1e2fc0d1da584d96033", "runtime": null}
|
|
|
|
|
{"task_id": "hard-sol-b-temporal_numeric-04", "family": "temporal_numeric", "split": "public", "group": "hard-sol-b-temporal_numeric-04", "ts": 1790798662.1849275, "status": "ok", "ok": true, "valid": true, "correct": false, "predicted": "narrow_fail", "ordinal_ev": null, "probs": {"clear_fail": 0.324620580367349, "narrow_fail": 0.6472762711048763, "pass": 0.02810314852777479}, "probs_as_returned": {"clear_fail": 0.324620580367349, "narrow_fail": 0.6472762711048763, "pass": 0.02810314852777479}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.056115685030817986, "usage": {"input_tokens": 363, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "071fa5d27e37148e268f6cd76bf33ca1bbe8d3d99d877f82dfae4e6495e30f5f", "runtime": null}
|
|
|
|
|
{"task_id": "hard-sol-c-judge_hard-03", "family": "judge_hard", "split": "public", "group": "hard-sol-c-judge_hard-03", "ts": 1790798662.2551572, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "no", "ordinal_ev": null, "probs": {"yes": 0.03075154512433679, "no": 0.9692484548756632}, "probs_as_returned": {"yes": 0.03075154512433679, "no": 0.9692484548756632}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05614997597876936, "usage": {"input_tokens": 509, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "8268dd3af9576ee8de0d0870e9f71bfd06de9e15157b39203016498fef22ac2b", "runtime": null}
|
|
|
|
|
{"task_id": "hard-sol-c-judge_hard-05", "family": "judge_hard", "split": "public", "group": "hard-sol-c-judge_hard-05", "ts": 1790798662.3209324, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "yes", "ordinal_ev": null, "probs": {"yes": 0.7318060856600669, "no": 0.2681939143399331}, "probs_as_returned": {"yes": 0.7318060856600669, "no": 0.2681939143399331}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05578163999598473, "usage": {"input_tokens": 471, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "be6c5ac5f5158d7a5de1a5e42e77126c9c047bffa77cc9641b7498ea2be10451", "runtime": null}
|
|
|
|
|
{"task_id": "hard-sol-c-judge_hard-07", "family": "judge_hard", "split": "public", "group": "hard-sol-c-judge_hard-07", "ts": 1790798662.387518, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "no", "ordinal_ev": null, "probs": {"yes": 0.2935240287234267, "no": 0.7064759712765734}, "probs_as_returned": {"yes": 0.2935240287234267, "no": 0.7064759712765734}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05563985102344304, "usage": {"input_tokens": 435, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "5294fc4d596ecabab9638cc1d8eb78b586dd0967b8d5e0b927f6f414da8dcb66", "runtime": null}
|
|
|
|
|
{"task_id": "hard-sol-c-judge_hard-08", "family": "judge_hard", "split": "public", "group": "hard-sol-c-judge_hard-08", "ts": 1790798662.4557378, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "no", "ordinal_ev": null, "probs": {"yes": 0.45308504361568214, "no": 0.5469149563843179}, "probs_as_returned": {"yes": 0.45308504361568214, "no": 0.5469149563843179}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.0556508349836804, "usage": {"input_tokens": 430, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "21bd927ea9b63e3d011584666c5b8df4a289563afc4549b1007932c57afc76b9", "runtime": null}
|
|
|
|
|
{"task_id": "hard-sol-c-judge_hard-09", "family": "judge_hard", "split": "public", "group": "hard-sol-c-judge_hard-09", "ts": 1790798662.5229077, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "yes", "ordinal_ev": null, "probs": {"yes": 0.7557061813028185, "no": 0.24429381869718148}, "probs_as_returned": {"yes": 0.7557061813028185, "no": 0.24429381869718148}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.055359949998091906, "usage": {"input_tokens": 460, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "f3ab59c31fa06068161c0d184f1fd1403688482264a87d4dc3febcd751ee162c", "runtime": null}
|
|
|
|
|
{"task_id": "hard-sol-c-judge_hard-10", "family": "judge_hard", "split": "public", "group": "hard-sol-c-judge_hard-10", "ts": 1790798662.5912318, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "yes", "ordinal_ev": null, "probs": {"yes": 0.8527907640733415, "no": 0.14720923592665847}, "probs_as_returned": {"yes": 0.8527907640733415, "no": 0.14720923592665847}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05610060004983097, "usage": {"input_tokens": 489, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "79836ba579472e71cf75dda4d6e439a1bf32e7055ad6fe2c4867f6d6cc06724b", "runtime": null}
|
|
|
|
|
{"task_id": "hard-sol-c-judge_hard-11", "family": "judge_hard", "split": "public", "group": "hard-sol-c-judge_hard-11", "ts": 1790798662.655868, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "no", "ordinal_ev": null, "probs": {"yes": 0.007439008670580321, "no": 0.9925609913294197}, "probs_as_returned": {"yes": 0.007439008670580321, "no": 0.9925609913294197}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05524129403056577, "usage": {"input_tokens": 460, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "36fd1eacaf9e0168a0616aaed05eef970ac47038bccf56580ade399ad9624c07", "runtime": null}
|
|
|
|
|
{"task_id": "hard-sol-c-judge_hard-13", "family": "judge_hard", "split": "public", "group": "hard-sol-c-judge_hard-13", "ts": 1790798662.7195992, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "no", "ordinal_ev": null, "probs": {"yes": 0.10012611628383591, "no": 0.8998738837161641}, "probs_as_returned": {"yes": 0.10012611628383591, "no": 0.8998738837161641}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.054972373007331043, "usage": {"input_tokens": 450, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "fcbf6678f80b0c0fb8f40b0a2fe4468817573c8c27723aea0469a79b6cc9f940", "runtime": null}
|
|
|
|
|
{"task_id": "hard-sol-c-judge_hard-15", "family": "judge_hard", "split": "public", "group": "hard-sol-c-judge_hard-15", "ts": 1790798662.785462, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "yes", "ordinal_ev": null, "probs": {"yes": 0.788764540067536, "no": 0.21123545993246395}, "probs_as_returned": {"yes": 0.788764540067536, "no": 0.21123545993246395}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.055583545996341854, "usage": {"input_tokens": 405, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "4cf2c928404e9231cbcf211ce428719105555dd507c9522d5e3c3fc9ca39f15d", "runtime": null}
|
|
|
|
|
{"task_id": "hard-sol-c-multi_hop-07", "family": "multi_hop", "split": "public", "group": "hard-sol-c-multi_hop-07", "ts": 1790798662.9308298, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "programme_review", "ordinal_ev": null, "probs": {"partial_release": 0.14708474951632727, "programme_review": 0.5492223588263985, "reject_draw": 0.15660814214094693, "release_draw": 0.14708474951632727}, "probs_as_returned": {"partial_release": 0.14708474951632727, "programme_review": 0.5492223588263985, "reject_draw": 0.15660814214094693, "release_draw": 0.14708474951632727}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.13299241696950048, "usage": {"input_tokens": 2615, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "e88cbc0405392455a47029214ec91ec2ba80c03f5eafd04b19aca979d8444553", "runtime": null}
|
|
|
|
|
{"task_id": "hard-sol-c-multi_hop-09", "family": "multi_hop", "split": "public", "group": "hard-sol-c-multi_hop-09", "ts": 1790798663.0799484, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "bus_substitution", "ordinal_ev": null, "probs": {"bus_substitution": 0.8215092246509226, "call_fen_cross": 0.02954865144756523, "pass_fen_cross": 0.11748026711353574, "terminate_oakmere": 0.03146185678797637}, "probs_as_returned": {"bus_substitution": 0.8215092246509226, "call_fen_cross": 0.02954865144756523, "pass_fen_cross": 0.11748026711353574, "terminate_oakmere": 0.03146185678797637}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.13484351203078404, "usage": {"input_tokens": 2637, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "cfa2e17b409c21ff5d3909beaae9a93248402c74d7138c532d01f70756649e51", "runtime": null}
|
|
|
|
|
{"task_id": "hard-sol-c-multi_hop-11", "family": "multi_hop", "split": "public", "group": "hard-sol-c-multi_hop-11", "ts": 1790798663.235058, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "coverage_excluded", "ordinal_ev": null, "probs": {"adjuster_referral": 0.06012453285478484, "coverage_confirmed": 0.04678050972661249, "coverage_excluded": 0.7873470051099877, "documentation_needed": 0.10574795230861497}, "probs_as_returned": {"adjuster_referral": 0.06012453285478484, "coverage_confirmed": 0.04678050972661249, "coverage_excluded": 0.7873470051099877, "documentation_needed": 0.10574795230861497}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.13914787000976503, "usage": {"input_tokens": 2715, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "9277b8d2d8360fbcc98033751c028ed6ac38f87bcbc97bdf22fff464ebe32463", "runtime": null}
|
|
|
|
|
{"task_id": "hard-sol-c-multi_hop-12", "family": "multi_hop", "split": "public", "group": "hard-sol-c-multi_hop-12", "ts": 1790798663.311927, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "conservation_hold", "ordinal_ev": null, "probs": {"conservation_hold": 0.9140935257634624, "deny_request": 0.024026050062128126, "digital_copy_only": 0.029001632737729627, "supervised_delivery": 0.03287879143667978}, "probs_as_returned": {"conservation_hold": 0.9140935257634624, "deny_request": 0.024026050062128126, "digital_copy_only": 0.029001632737729627, "supervised_delivery": 0.03287879143667978}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.064269979018718, "usage": {"input_tokens": 658, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "bc597207da2c81e5751b90136d566e3a4b84735d19496436ce7657e533132f04", "runtime": null}
|
|
|
|
|
{"task_id": "hard-sol-c-multi_hop-13", "family": "multi_hop", "split": "public", "group": "hard-sol-c-multi_hop-13", "ts": 1790798663.4657333, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "normal_release", "ordinal_ev": null, "probs": {"engineering_review": 0.022049499850414715, "normal_release": 0.9510435155444504, "rework": 0.011774210282422209, "scrap_lot": 0.015132774322712624}, "probs_as_returned": {"engineering_review": 0.022049499850414715, "normal_release": 0.9510435155444504, "rework": 0.011774210282422209, "scrap_lot": 0.015132774322712624}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.13704001996666193, "usage": {"input_tokens": 2683, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "7121b6a8de53dd46df590299ed2e504449be5bbcb1980f10aaa0eb304e66dcfe", "runtime": null}
|