| # | Model | Provider | Type | Score | |
|---|---|---|---|---|---|
| 1 | Qwen3.7 Max | Alibaba | Closed | 44.5% | |
| 2 | DeepSeek V4 Pro (Max) | DeepSeek | Open | 38.3% | |
| 3 | DeepSeek V4 Flash (Max) | DeepSeek | Open | 33.0% | |
| 4 | ZAYA1-8B | Zyphra | Open | 32.2% | |
| 5 | DeepSeek V4 Pro (High) | DeepSeek | Open | 27.4% | |
| 6 | DeepSeek V4 Flash (High) | DeepSeek | Open | 19.1% | |
| 7 | DeepSeek V4 Flash | DeepSeek | Open | 1.0% | |
| 8 | DeepSeek V4 Pro | DeepSeek | Open | 0.4% |