hle With Tools
6 models evaluated
|
| 1 | Qwen3.7 Max | Alibaba | Closed | 53.5% | |
| 2 | DeepSeek V4 Pro (Max) | DeepSeek | Open | 48.2% | |
| 3 | Step 3.7 Flash | StepFun | Open | 47.2% | |
| 4 | DeepSeek V4 Flash (Max) | DeepSeek | Open | 45.1% | |
| 5 | DeepSeek V4 Pro (High) | DeepSeek | Open | 44.7% | |
| 6 | DeepSeek V4 Flash (High) | DeepSeek | Open | 40.3% | |