| 1 | Claude Opus 5 | Anthropic | Closed | claude-opus-5 | |
| 2 | GPT-5.6 Sol | OpenAI | Closed | gpt-5-6-sol | |
| 3 | Claude Fable 5 | Anthropic | Closed | claude-fable-5 | |
| 4 | Kimi K3 | Moonshot AI · Closed | 50.1% | | |
| 5 | GPT-5.6 Terra | OpenAI · Closed | 47.4% | | |
| 6 | Claude Opus 4.8 | Anthropic · Closed | 47.2% | | |
| 7 | Claude Sonnet 5 | Anthropic · Closed | 46.7% | | |
| 8 | Grok 4.5 | xAI · Closed | 45.7% | | |
| 9 | GPT-5.6 Luna | OpenAI · Closed | 45.6% | | |
| 10 | GPT-5.5 | OpenAI · Closed | 44.9% | | |
| 11 | Claude Opus 4.7 (Adaptive) | Anthropic · Closed | 44.4% | | |
| 12 | GLM-5.2 | Z.AI · Open weight | 43.1% | | |
| 13 | GPT-5.4 | OpenAI · Closed | 41.1% | | |
| 14 | Gemini 3.6 Flash | Google · Closed | 38.7% | | |
| 15 | Muse Spark 1.1 | Meta · Closed | 37.5% | | |
| 16 | Gemini 3.5 Flash | Google · Closed | 37.5% | | |
| 17 | DeepSeek V4 Pro (Max) | DeepSeek · Open weight | 36.4% | | |
| 18 | MiniMax M3 | MiniMax · Open weight | 35.4% | | |
| 19 | DeepSeek V4 Pro (High) | DeepSeek · Open weight | 34.4% | | |
| 20 | Inkling | Thinking Machines Lab · Open weight | 32.3% | | |
| 21 | DeepSeek V4 Flash (Max) | DeepSeek · Open weight | 31.1% | | |
| 22 | Hy3 Preview | Tencent · Open weight | 30.7% | | |
| 23 | Hy3 | Tencent · Open weight | 30.7% | | |
| 24 | Qwen3.7 Max | Alibaba · Closed | 30.6% | | |
| 25 | Kimi K2.6 | Moonshot AI · Open weight | 30.3% | | |
| 26 | GPT-5.4 mini | OpenAI · Closed | 30.2% | | |
| 27 | GLM-5.1 | Z.AI · Open weight | 29.9% | | |
| 28 | Kimi K2.7 Code | Moonshot AI · Open weight | 29.6% | | |
| 29 | MiMo-V2.5-Pro | Xiaomi · Closed | 29.1% | | |
| 30 | Muse Spark | Meta · Closed | 28.7% | | |
| 31 | DeepSeek V4 Flash (High) | DeepSeek · Open weight | 28.2% | | |
| 32 | Qwen3.6 Plus | Alibaba · Closed | 27.6% | | |
| 33 | GPT-5.4 nano | OpenAI · Closed | 27.5% | | |
| 34 | Nemotron 3 Ultra | NVIDIA · Open weight | 27.4% | | |
| 35 | Qwen3.6-27B | Alibaba · Open weight | 27.0% | | |
| 36 | Gemini 3.5 Flash-Lite | Google · Closed | 26.8% | | |
| 37 | GPT-5 (high) | OpenAI · Closed | 25.7% | | |
| 38 | MiniMax M2.7 | MiniMax · Open weight | 25.6% | | |
| 39 | GLM-4.7 | Z.AI · Open weight | 25.4% | | |
| 40 | Grok 4.3 | xAI · Closed | 24.1% | | |
| 41 | Kimi K2.5 | Moonshot AI · Open weight | 21.7% | | |
| 42 | Kimi K2.5 (Reasoning) | Moonshot AI · Closed | 21.7% | | |
| 43 | Step 3.7 Flash | StepFun · Open weight | 21.5% | | |
| 44 | Qwen3.6-35B-A3B | Alibaba · Open weight | 21.4% | | |
| 45 | Gemini 3.1 Pro | Google · Closed | 21.4% | | |
| 46 | GPT-5.1 | OpenAI · Closed | 21.0% | | |
| 47 | Qwen3.7 Plus | Alibaba · Closed | 20.8% | | |
| 48 | Qwen3.5-122B-A10B | Alibaba · Open weight | 20.7% | | |
| 49 | Qwen3.5 397B | Alibaba · Open weight | 19.9% | | |
| 50 | Qwen3.5 397B (Reasoning) | Alibaba · Open weight | 19.9% | | |
| 51 | GPT-5 mini | OpenAI · Closed | 19.4% | | |
| 52 | Mistral Medium 3.5 128B | Mistral · Open weight | 19.0% | | |
| 53 | Gemma 4 31B | Google · Open weight | 14.4% | | |
| 54 | GPT-OSS 120B | OpenAI · Open weight | 13.2% | | |
| 55 | MiMo-V2-Flash | Xiaomi · Open weight | 12.0% | | |
| 56 | Gemma 4 26B A4B | Google · Open weight | 11.0% | | |
| 57 | Mercury 2 | Inception · Closed | 9.6% | | |
| 58 | Command A+ | Cohere · Open weight | 9.2% | | |
| 59 | Nemotron 3 Super 120B A12B | NVIDIA · Open weight | 8.7% | | |
| 60 | K-Exaone | LG AI Research · Closed | 8.0% | | |
| 61 | Gemma 4 12B | Google · Open weight | 7.9% | | |
| 62 | Gemini 2.5 Pro | Google · Closed | 7.1% | | |
| 63 | Gemini 3.1 Flash-Lite | Google · Closed | 6.2% | | |
| 64 | Mistral Large 3 | Mistral · Closed | 5.5% | | |
| 65 | Mistral Small 4 | Mistral · Open weight | 4.7% | | |
| 66 | Mistral Small 4 (Reasoning) | Mistral · Open weight | 4.7% | | |
| 67 | Trinity-Large-Preview | Arcee AI · Open weight | 3.6% | | |
| 68 | Trinity-Large-Thinking | Arcee AI · Open weight | 3.6% | | |
| 69 | GPT-OSS 20B | OpenAI · Open weight | 3.1% | | |
| 70 | Ling 2.6 Flash | InclusionAI · Open weight | 2.3% | | |
| 71 | Ministral 3 14B (Reasoning) | Mistral · Open weight | 2.2% | | |
| 72 | Ministral 3 14B | Mistral · Open weight | 2.2% | | |
| 73 | Nemotron 3 Nano 30B | NVIDIA · Open weight | 2.0% | | |
| 74 | Gemma 4 E4B | Google · Open weight | 1.8% | | |
| 75 | GPT-4.1 mini | OpenAI · Closed | 1.7% | | |
| 76 | DeepSeek V3 | DeepSeek · Open weight | 1.6% | | |
| 77 | Ministral 3 3B (Reasoning) | Mistral · Open weight | 1.6% | | |
| 78 | Ministral 3 3B | Mistral · Open weight | 1.6% | | |
| 79 | Gemma 4 E2B | Google · Open weight | 1.5% | | |
| 80 | Llama 4 Maverick | Meta · Open weight | 1.3% | | |
| 81 | Ministral 3 8B (Reasoning) | Mistral · Open weight | 1.2% | | |
| 82 | Ministral 3 8B | Mistral · Open weight | 1.2% | | |
| 83 | GPT-4.1 nano | OpenAI · Closed | 1.2% | | |
| 84 | Llama 4 Scout | Meta · Open weight | 1.1% | | |
| 85 | GPT-4o mini | OpenAI · Closed | 1.0% | | |
| 86 | Gemma 3 27B | Google · Open weight | 0.3% | | |