← τ-bench leaderboards

Telecom · Standard · pass^3

τ-bench · 8 models

RankModelScore
1Qwen3.5-397B-A17B93.86
2Claude Opus 4.581.36
3Gemini 3 Pro79.17
4GPT-5.276.75
5Gemini 3 Flash76.54
6Claude Sonnet 4.568.86
7GLM-568.2
8GPT-5.235.5263