feat: add benchmark scorer (#444)

* fix: improve print output of scorers * feat: add benchmark scorer
2026-09-27 06:21:29 -07:00 · 2026-09-03 17:49:46 +05:30
parent c7a44f0db7
commit 95dda4c4db
11 changed files with 113 additions and 40 deletions
@@ -20,6 +20,8 @@ residual_plot_label = "Humorous prompts"
 residual_plot_color = "darkorange"

 [scorer.KeywordRate]
+score_name = "Responses with humor"
+
 keyword_markers = [
    "😅",
    "here's one",