List your company

Agentic Tasks on Tau2 Airline

64ScoreGPT-5.1 (Medium)
35.71243.05650.457.744Jan 3, 2026Jan 4, 2026Jan 5, 2026Jan 7, 2026Jan 8, 2026Jan 9, 2026Jan 11, 2026

Evaluation results

MethodLinks
GPT-5.1 (Medium)User-simulator=GPT-4.12026.0164
GPT-5.1 (Medium)User-simulator=GPT-5.12026.0164
GLM-4.5-AirNumber of Parameters=110B2026.0160.8
HyperCLOVA X 32B ThinkUser-simulator=GPT-4.12026.0158
HyperCLOVA X 32B ThinkUser-simulator=GPT-5.12026.0158
gpt-oss-120bNumber of Parameters=117B, Optimization Level=high2026.0156
gpt-oss-120bNumber of Parameters=117B, Optimization Level=medium2026.0152.8
Solar OpenNumber of Parameters=102B2026.0152.4
Qwen3 235B-A22BUser-simulator=GPT-5.12026.0141.6
Qwen3 235B-A22BUser-simulator=GPT-4.12026.0136.8