List your company

Customer Support Interaction on τ-Bench Telecom Verified (test)

94Pass@1Gemini-3-flash
25.3643.186178.82May 27, 2026

Evaluation results

MethodLinks
Gemini-3-flashUser Simulator=GPT-5.22026.0594
Gemini-3-flashUser Simulator=Gemini-3-flash2026.0590
claude-sonnet-4.6User Simulator=Gemini-3-flash2026.0581
deepseek-3.1User Simulator=GPT-5.22026.0580
GPT-5.2User Simulator=GPT-5.22026.0562
GPT-5.2User Simulator=Gemini-3-flash2026.0555
deepseek-3.1User Simulator=Gemini-3-flash2026.0553
Gemini-2.5-flashUser Simulator=GPT-5.22026.0546
Qwen-32BUser Simulator=Gemini-3-flash2026.0540
Gemini-2.5-flashUser Simulator=Gemini-3-flash2026.0535
Qwen-32BUser Simulator=GPT-5.22026.0528