Airline · Standard · pass^2
τ-bench · 8 models
| Rank | Model | Score |
|---|---|---|
| 1 | GPT-5.2 | 78.33 |
| 2 | Claude Opus 4.5 | 77.67 |
| 3 | Gemini 3 Flash | 76.33 |
| 4 | GLM-5 | 76 |
| 5 | Qwen3.5-397B-A17B | 75.67 |
| 6 | Gemini 3 Pro | 74.67 |
| 7 | Claude Sonnet 4.5 | 62 |
| 8 | GPT-5.2 | 35.6667 |
τ-bench · 8 models
| Rank | Model | Score |
|---|---|---|
| 1 | GPT-5.2 | 78.33 |
| 2 | Claude Opus 4.5 | 77.67 |
| 3 | Gemini 3 Flash | 76.33 |
| 4 | GLM-5 | 76 |
| 5 | Qwen3.5-397B-A17B | 75.67 |
| 6 | Gemini 3 Pro | 74.67 |
| 7 | Claude Sonnet 4.5 | 62 |
| 8 | GPT-5.2 | 35.6667 |