| # | Model | Provider | Type | Score | |
|---|---|---|---|---|---|
| 1 | Kimi K2.6 | Moonshot AI | Open | 96.4% | |
| 2 | GLM-5 | Z.AI | Open | 95.8% | |
| 3 | Kimi K2.5 | Moonshot AI | Open | 95.8% | |
| 4 | GLM-5.1 | Z.AI | Open | 95.3% | |
| 5 | Qwen3.6 Plus | Alibaba | Closed | 95.3% | |
| 6 | Claude Opus 4.5 | Anthropic | Closed | 95.1% | |
| 7 | Qwen3.6-27B | Alibaba | Open | 94.1% | |
| 8 | Qwen3.5 397B | Alibaba | Open | 93.3% | |
| 9 | Qwen3.6-35B-A3B | Alibaba | Open | 92.7% | |
| 10 | ZAYA1-8B | Zyphra | Open | 89.1% | |
| 11 | ZAYA1-74B-Preview | Zyphra | Open | 76.4% | |
| 12 | LFM2.5-8B-A1B | LiquidAI | Open | 50.0% | |
| 13 | MiniCPM5-1B | OpenBMB | Open | 40.4% |