Retail · Standard · pass^3
τ-bench · 8 models
| Rank | Model | Score |
|---|---|---|
| 1 | Qwen3.5-397B-A17B | 66.45 |
| 2 | GPT-5.2 | 59.87 |
| 3 | Claude Opus 4.5 | 58.77 |
| 4 | Gemini 3 Flash | 57.89 |
| 5 | Gemini 3 Pro | 54.39 |
| 6 | GPT-5.2 | 53.0702 |
| 7 | GLM-5 | 51.1 |
| 8 | Claude Sonnet 4.5 | 47.37 |
τ-bench · 8 models
| Rank | Model | Score |
|---|---|---|
| 1 | Qwen3.5-397B-A17B | 66.45 |
| 2 | GPT-5.2 | 59.87 |
| 3 | Claude Opus 4.5 | 58.77 |
| 4 | Gemini 3 Flash | 57.89 |
| 5 | Gemini 3 Pro | 54.39 |
| 6 | GPT-5.2 | 53.0702 |
| 7 | GLM-5 | 51.1 |
| 8 | Claude Sonnet 4.5 | 47.37 |