← τ-bench leaderboards

Telecom · Standard · pass^4

τ-bench · 8 models

RankModelScore
1Qwen3.5-397B-A17B92.11
2Claude Opus 4.578.07
3Gemini 3 Pro74.56
4GPT-5.271.93
5Gemini 3 Flash70.18
6Claude Sonnet 4.564.04
7GLM-562.28
8GPT-5.230.7018