Telecom · Standard · pass^2
τ-bench · 8 models
| Rank | Model | Score |
|---|---|---|
| 1 | Qwen3.5-397B-A17B | 95.76 |
| 2 | Claude Opus 4.5 | 86.11 |
| 3 | Gemini 3 Pro | 84.5 |
| 4 | Gemini 3 Flash | 83.48 |
| 5 | GPT-5.2 | 82.46 |
| 6 | GLM-5 | 76.32 |
| 7 | Claude Sonnet 4.5 | 75.44 |
| 8 | GPT-5.2 | 42.8363 |
τ-bench · 8 models
| Rank | Model | Score |
|---|---|---|
| 1 | Qwen3.5-397B-A17B | 95.76 |
| 2 | Claude Opus 4.5 | 86.11 |
| 3 | Gemini 3 Pro | 84.5 |
| 4 | Gemini 3 Flash | 83.48 |
| 5 | GPT-5.2 | 82.46 |
| 6 | GLM-5 | 76.32 |
| 7 | Claude Sonnet 4.5 | 75.44 |
| 8 | GPT-5.2 | 42.8363 |