| # | Model | Provider | Type | Score | |
|---|---|---|---|---|---|
| 1 | GLM-5.2 | Z.AI | Open | glm-5-2 | |
| 2 | Inkling | Thinking Machines Lab | Open | inkling | |
| 3 | Kimi K2.6 | Moonshot AI | Open | kimi-2-6 | |
| 4 | GLM-5 | Z.AI · Open weight | 95.8% | ||
| 5 | Kimi K2.5 | Moonshot AI · Open weight | 95.8% | ||
| 6 | GLM-5.1 | Z.AI · Open weight | 95.3% | ||
| 7 | Qwen3.6 Plus | Alibaba · Closed | 95.3% | ||
| 8 | Claude Opus 4.5 | Anthropic · Closed | 95.1% | ||
| 9 | MAI-Thinking-1 | Microsoft · Closed | 94.5% | ||
| 10 | Qwen3.6-27B | Alibaba · Open weight | 94.1% | ||
| 11 | Qwen3.5 397B | Alibaba · Open weight | 93.3% | ||
| 12 | Qwen3.6-35B-A3B | Alibaba · Open weight | 92.7% | ||
| 13 | ZAYA1-8B | Zyphra · Open weight | 89.1% | ||
| 14 | Gemma 4 12B | Google · Open weight | 77.5% | ||
| 15 | ZAYA1-74B-Preview | Zyphra · Open weight | 76.4% | ||
| 16 | LFM2.5-8B-A1B | LiquidAI · Open weight | 50.0% | ||
| 17 | MiniCPM5-1B | OpenBMB · Open weight | 40.4% |