| # | Model | Provider | Type | Score | |
|---|---|---|---|---|---|
| 1 | DeepSeek V4 Pro (Max) | DeepSeek | Open | 93.5% | |
| 2 | Qwen3.7 Max | Alibaba | Closed | 91.6% | |
| 3 | DeepSeek V4 Flash (Max) | DeepSeek | Open | 91.6% | |
| 4 | DeepSeek V4 Pro (High) | DeepSeek | Open | 89.8% | |
| 5 | Kimi K2.6 | Moonshot AI | Open | 89.6% | |
| 6 | DeepSeek V4 Flash (High) | DeepSeek | Open | 88.4% | |
| 7 | Kimi K2.5 | Moonshot AI | Open | 85% | |
| 8 | GLM-4.7 | Z.AI | Open | 84.9% | |
| 9 | Qwen3.6-27B | Alibaba | Open | 83.9% | |
| 10 | Qwen3.6-35B-A3B | Alibaba | Open | 80.4% | |
| 11 | Nemotron 3 Nano Omni 30B A3B | NVIDIA | Open | 63.2% | |
| 12 | DeepSeek V4 Pro | DeepSeek | Open | 56.8% | |
| 13 | DeepSeek V4 Flash | DeepSeek | Open | 55.2% | |
| 14 | DeepSeek V3 | DeepSeek | Open | 37.6% |