| 1 | Sakana Fugu-Ultra | Sakana AI | Proprietary | 93.2% | |
| 2 | Sakana Fugu | Sakana AI | Proprietary | 92.9% | |
| 3 | Qwen3.8-Omni-Flash | Alibaba | Proprietary | 92.6% | |
| 4 | Solar Open 2 | Upstage · Open weight | 92.4% | | |
| 5 | Qwen3.8-Flash-Next | Alibaba · Open weight | 91.9% | | |
| 6 | dots3-note Preview | Dots Studio · Open weight | 91.5% | | |
| 7 | Qwen3.8-27B | Alibaba · Open weight | 90.3% | | |
| 8 | Ternary Bonsai 2 27B | Prism ML · Open weight | 90.1% | | |
| 9 | Kimi K2.6 | Moonshot AI · Open weight | 89.6% | | |
| 10 | Nemotron 3 Ultra | NVIDIA · Open weight | 89.0% | | |
| 11 | BTL-3 | Bad Theory Labs · Open weight | 88.1% | | |
| 12 | MAI-Thinking-1 | Microsoft · Closed | 87.7% | | |
| 13 | Qwen3.6 Plus | Alibaba · Closed | 87.1% | | |
| 14 | Kimi K2.5 | Moonshot AI · Open weight | 85.0% | | |
| 15 | Claude Opus 4.5 | Anthropic · Closed | 84.8% | | |
| 16 | A.X K2 | SK Telecom · Open weight | 84.0% | | |
| 17 | Qwen3.5 397B | Alibaba · Open weight | 83.6% | | |
| 18 | Granite 4.2 30B | IBM · Open weight | 75.8% | | |
| 19 | Granite 4.2 8B | IBM · Open weight | 73.2% | | |
| 20 | Gemma 4 12B | Google · Open weight | 72.0% | | |
| 21 | Mellum2-12B-A2.5B-Thinking | JetBrains · Open weight | 69.9% | | |
| 22 | Granite 4.2 3B | IBM · Open weight | 69.7% | | |
| 23 | MiniCPM5-2B | OpenBMB · Open weight | 69.1% | | |
| 24 | BTL-4 | Bad Theory Labs · Open weight | 66.1% | | |
| 25 | ZAYA1-8B | Zyphra · Open weight | 65.8% | | |
| 26 | ZAYA1-74B-Preview | Zyphra · Open weight | 65.7% | | |
| 27 | Agents-A1-4B | InternScience · Open weight | 59.6% | | |
| 28 | LFM2.5-2.6B | LiquidAI · Open weight | 59.4% | | |
| 29 | Mellum2-12B-A2.5B-Instruct | JetBrains · Open weight | 37.2% | | |
| 30 | MiniCPM5-1B | OpenBMB · Open weight | 33.5% | | |
| 31 | LLaDA2.2-mini | InclusionAI · Open weight | 28.1% | | |