| 1 | Claude Opus 5.5 | Anthropic | Proprietary | 64.4% | |
| 2 | Claude Fable 5.1 | Anthropic | Proprietary | 60.9% | |
| 3 | Claude Mythos 5 | Anthropic | Proprietary | 59% | |
| 4 | Claude Opus 5 | Anthropic · Closed | 56.3% | | |
| 5 | Muse Spark 1.1 | Meta · Closed | 52.2% | | |
| 6 | Sakana Fugu-Ultra | Sakana AI · Closed | 50% | | |
| 7 | Claude Opus 4.8 | Anthropic · Closed | 49.8% | | |
| 8 | Pareto 26.9 | Unbiased · Closed | 49% | | |
| 9 | Sakana Fugu | Sakana AI · Closed | 47.2% | | |
| 10 | Claude Opus 4.7 (Adaptive) | Anthropic · Closed | 46.9% | | |
| 11 | Gemini 3.1 Pro | Google · Closed | 45.4% | | |
| 12 | Ornith-1.5-397B | Ornith AI · Open weight | 44.6% | | |
| 13 | Qwen3.8 Max | Alibaba · Open weight | 43.6% | | |
| 14 | Kimi K3 | Moonshot AI · Closed | 43.5% | | |
| 15 | Hy4 preview | Tencent · Open weight | 43.4% | | |
| 16 | Claude Sonnet 5 | Anthropic · Closed | 43.2% | | |
| 17 | GPT-5.5 Pro | OpenAI · Closed | 43.1% | | |
| 18 | Muse Spark | Meta · Closed | 42.8% | | |
| 19 | GPT-5.4 Pro | OpenAI · Closed | 42.7% | | |
| 20 | GPT-5.5 | OpenAI · Closed | 41.4% | | |
| 21 | GLM-5.2 | Z.AI · Open weight | 40.5% | | |
| 22 | Claude Opus 4.6 | Anthropic · Closed | 40% | | |
| 23 | GPT-5.4 | OpenAI · Closed | 39.8% | | |
| 24 | Qwen3.8-Flash-Next | Alibaba · Open weight | 35.9% | | |
| 25 | MiMo-V2.5-Pro | Xiaomi · Closed | 34% | | |
| 26 | Inkling-Small | Thinking Machines Lab · Open weight | 31.6% | | |
| 27 | Grok 4.20 | xAI · Closed | 31.6% | | |
| 28 | Qwen3.8-27B | Alibaba · Open weight | 30.8% | | |
| 29 | Inkling | Thinking Machines Lab · Open weight | 30% | | |
| 30 | Solar Open 2 | Upstage · Open weight | 28.8% | | |
| 31 | GPT-5.4 mini | OpenAI · Closed | 28.2% | | |
| 32 | Nemotron 3 Ultra | NVIDIA · Open weight | 26.7% | | |
| 33 | Ornith-1.5-35B-A3B | Ornith AI · Open weight | 25.6% | | |
| 34 | GPT-5.4 nano | OpenAI · Closed | 24.3% | | |
| 35 | Ornith-1.5-9B | Ornith AI · Open weight | 20.2% | | |
| 36 | Gemma 4 31B | Google · Open weight | 19.5% | | |
| 37 | Nemotron 3.5 Lightning 30B A3B NVFP4 | NVIDIA · Open weight | 10.5% | | |
| 38 | Gemma 4 26B A4B | Google · Open weight | 8.7% | | |
| 39 | Gemma 4 12B | Google · Open weight | 5.2% | | |