Agentic Tasks on Tau2 Airline
64ScoreGPT-5.1 (Medium)
Evaluation Results
| Method | Links | |
|---|---|---|
| GPT-5.1 (Medium)User-simulator=GPT-4.12026.01 | 64 | |
| GPT-5.1 (Medium)User-simulator=GPT-5.12026.01 | 64 | |
| GLM-4.5-AirNumber of Parameters=110B2026.01 | 60.8 | |
| HyperCLOVA X 32B ThinkUser-simulator=GPT-4.12026.01 | 58 | |
| HyperCLOVA X 32B ThinkUser-simulator=GPT-5.12026.01 | 58 | |
| gpt-oss-120bNumber of Parameters=117B, Optimization Level=high2026.01 | 56 | |
| gpt-oss-120bNumber of Parameters=117B, Optimization Level=medium2026.01 | 52.8 | |
| Solar OpenNumber of Parameters=102B2026.01 | 52.4 | |
| Qwen3 235B-A22BUser-simulator=GPT-5.12026.01 | 41.6 | |
| Qwen3 235B-A22BUser-simulator=GPT-4.12026.01 | 36.8 |