| # | Model | Provider | Type | Score | |
|---|---|---|---|---|---|
| 1 | Qwen3.7 Max | Alibaba | Closed | 53.5% | |
| 2 | Gemini 3.5 Flash | Closed | 53.1% | ||
| 3 | Kimi K2.6 | Moonshot AI | Open | 52.2% | |
| 4 | Kimi K2.5 | Moonshot AI | Open | 48.7% | |
| 5 | Grok 4.3 | xAI | Closed | 47.3% | |
| 6 | Qwen 3.6 Max (preview) | Alibaba | Closed | 47% | |
| 7 | Hy3 Preview | Tencent | Open | 41.2% | |
| 8 | Nemotron 3 Nano Omni 30B A3B | NVIDIA | Open | 32% | |
| 9 | Ling 2.6 Flash | InclusionAI | Open | 27% |