Skip to content
Slow Variables
Ask

Indicators / series

tau2_bench.gpt_5_4.banking_knowledge_pass_1.pt

Source: Sierra tau2-bench leaderboard (pass^k per model and domain) (Sierra) · Sierra; public leaderboard data, cited with attribution · CSV

Sierra, tau2-bench leaderboard

idvaluegradeas of datepublished datetieraudited vs reportedextraction methodreview statusretrieved athttp statuscontent hashsupersedes idurlflags
3676db502e8fe6b839.4%grade A, evidence tier 12026-03-252026-09-101reportedapiapproved2026-09-25 07:3220047fa11691a74—source page
Raw snippets and dispute text
  • 3676db502e8fe6b8 GPT-5.4 (Sierra) banking_knowledge pass_1 39.43