List your company

Customer Support Interaction on τc-Bench Airline Ours (test)

64Pass@1claude-sonnet-4.6
7.8422.423751.58May 27, 2026

Evaluation results

MethodLinks
claude-sonnet-4.6User Simulator=Gemini-3-flash2026.0564—
Gemini-3-flashUser Simulator=GPT-5.22026.055628
GPT-5.2User Simulator=Gemini-3-flash2026.054926
deepseek-3.1User Simulator=Gemini-3-flash2026.054116
Gemini-2.5-flashUser Simulator=GPT-5.22026.05368
deepseek-3.1User Simulator=GPT-5.22026.053618
Gemini-3-flashUser Simulator=Gemini-3-flash2026.053422
GPT-5.2User Simulator=GPT-5.22026.053420
Gemini-2.5-flashUser Simulator=Gemini-3-flash2026.052110
Qwen-32BUser Simulator=Gemini-3-flash2026.05136
Qwen-32BUser Simulator=GPT-5.22026.05106