| # | Model | Provider | Type | Score | |
|---|---|---|---|---|---|
| 1 | Grok 4.3 | xAI | Closed | 81.3% | |
| 2 | Qwen3.7 Max | Alibaba | Closed | 79.1% | |
| 3 | Gemini 3.5 Flash | Closed | 76.3% | ||
| 4 | Qwen3.6 Plus | Alibaba | Closed | 75.8% | |
| 5 | Nemotron 3 Nano Omni 30B A3B | NVIDIA | Open | 74.2% | |
| 6 | Hy3 Preview | Tencent | Open | 63.1% | |
| 7 | Claude Opus 4.5 | Anthropic | Closed | 58% | |
| 8 | Ling 2.6 Flash | InclusionAI | Open | 57% | |
| 9 | LFM2.5-8B-A1B | LiquidAI | Open | 56.5% | |
| 10 | ZAYA1-8B | Zyphra | Open | 52.6% | |
| 11 | MiniCPM5-1B | OpenBMB | Open | 46.7% |