| 1 | Claude Fable 5 | Anthropic | Closed | claude-fable-5 | |
| 2 | Claude Opus 5 | Anthropic | Closed | claude-opus-5 | |
| 3 | GPT-5.6 Sol | OpenAI | Closed | gpt-5-6-sol | |
| 4 | Claude Opus 4.8 | Anthropic · Closed | 45.7% | | |
| 5 | Muse Spark 1.1 | Meta · Closed | 45.1% | | |
| 6 | Gemini 3.1 Pro | Google · Closed | 44.7% | | |
| 7 | Kimi K3 | Moonshot AI · Closed | 44.3% | | |
| 8 | GPT-5.5 | OpenAI · Closed | 44.3% | | |
| 9 | GPT-5.6 Terra | OpenAI · Closed | 41.8% | | |
| 10 | GPT-5.4 | OpenAI · Closed | 41.6% | | |
| 11 | Gemini 3.5 Flash | Google · Closed | 41.0% | | |
| 12 | Grok 4.5 | xAI · Closed | 40.3% | | |
| 13 | GLM-5.2 | Z.AI · Open weight | 40.1% | | |
| 14 | GPT-5.3 Codex | OpenAI · Closed | 39.9% | | |
| 15 | Muse Spark | Meta · Closed | 39.9% | | |
| 16 | GPT-5.3-Codex-Spark | OpenAI · Closed | 39.9% | | |
| 17 | Claude Sonnet 5 | Anthropic · Closed | 39.6% | | |
| 18 | Claude Opus 4.7 (Adaptive) | Anthropic · Closed | 39.6% | | |
| 19 | Gemini 3.6 Flash | Google · Closed | 38.3% | | |
| 20 | Qwen3.7 Max | Alibaba · Closed | 38.1% | | |
| 21 | GPT-5.6 Luna | OpenAI · Closed | 37.2% | | |
| 22 | Gemini 3 Pro | Google · Closed | 37.2% | | |
| 23 | MiniMax M3 | MiniMax · Open weight | 37.1% | | |
| 24 | Claude Opus 4.6 (Adaptive) | Anthropic · Closed | 36.7% | | |
| 25 | DeepSeek V4 Pro (Max) | DeepSeek · Open weight | 35.9% | | |
| 26 | Kimi K2.6 | Moonshot AI · Open weight | 35.9% | | |
| 27 | GPT-5.2 | OpenAI · Closed | 35.4% | | |
| 28 | Grok 4.3 | xAI · Closed | 35.0% | | |
| 29 | MiMo-V2.5-Pro | Xiaomi · Closed | 33.8% | | |
| 30 | DeepSeek V4 Pro (High) | DeepSeek · Open weight | 33.5% | | |
| 31 | GPT-5.2-Codex | OpenAI · Closed | 33.5% | | |
| 32 | Qwen3.7 Plus | Alibaba · Closed | 33.4% | | |
| 33 | Kimi K2.7 Code | Moonshot AI · Open weight | 32.8% | | |
| 34 | DeepSeek V4 Flash (Max) | DeepSeek · Open weight | 32.1% | | |
| 35 | Hy3 Preview | Tencent · Open weight | 31.6% | | |
| 36 | Hy3 | Tencent · Open weight | 31.6% | | |
| 37 | Claude Opus 4.7 | Anthropic · Closed | 31.2% | | |
| 38 | Inkling | Thinking Machines Lab · Open weight | 29.7% | | |
| 39 | Kimi K2.5 | Moonshot AI · Open weight | 29.4% | | |
| 40 | Kimi K2.5 (Reasoning) | Moonshot AI · Closed | 29.4% | | |
| 41 | Qwen 3.6 Max (preview) | Alibaba · Closed | 28.9% | | |
| 42 | Claude Opus 4.5 Thinking | Anthropic · Closed | 28.4% | | |
| 43 | MiMo-V2-Pro | Xiaomi · Closed | 28.3% | | |
| 44 | MiniMax M2.7 | MiniMax · Open weight | 28.1% | | |
| 45 | GLM-5.1 | Z.AI · Open weight | 28.0% | | |
| 46 | DeepSeek V4 Flash (High) | DeepSeek · Open weight | 27.8% | | |
| 47 | Qwen3.5 397B | Alibaba · Open weight | 27.3% | | |
| 48 | Qwen3.5 397B (Reasoning) | Alibaba · Open weight | 27.3% | | |
| 49 | GLM-5 | Z.AI · Open weight | 27.2% | | |
| 50 | GPT-5.4 mini | OpenAI · Closed | 26.6% | | |
| 51 | Nemotron 3 Ultra | NVIDIA · Open weight | 26.6% | | |
| 52 | GPT-5.4 nano | OpenAI · Closed | 26.5% | | |
| 53 | GPT-5.1 | OpenAI · Closed | 26.5% | | |
| 54 | GPT-5 (high) | OpenAI · Closed | 26.5% | | |
| 55 | Qwen3.6 Plus | Alibaba · Closed | 25.7% | | |
| 56 | GLM-5-Turbo | Z.AI · Closed | 25.4% | | |
| 57 | GLM-4.7 | Z.AI · Open weight | 25.1% | | |
| 58 | Grok 4 | xAI · Closed | 23.9% | | |
| 59 | GPT-5 (medium) | OpenAI · Closed | 23.5% | | |
| 60 | Qwen3.5-122B-A10B | Alibaba · Open weight | 23.4% | | |
| 61 | GPT-5.1-Codex-Max | OpenAI · Closed | 23.4% | | |
| 62 | GPT-5.1-Codex | OpenAI · Closed | 23.4% | | |
| 63 | Gemma 4 31B | Google · Open weight | 22.7% | | |
| 64 | Step 3.5 Flash | StepFun · Open weight | 22.6% | | |
| 65 | Qwen3.5-27B | Alibaba · Open weight | 22.2% | | |
| 66 | Qwen3.6-27B | Alibaba · Open weight | 21.6% | | |
| 67 | Gemini 2.5 Pro | Google · Closed | 21.1% | | |
| 68 | Qwen3.6-35B-A3B | Alibaba · Open weight | 20.2% | | |
| 69 | o3 | OpenAI · Closed | 20.0% | | |
| 70 | Step 3.7 Flash | StepFun · Open weight | 19.9% | | |
| 71 | MiMo-V2-Omni | Xiaomi · Closed | 19.9% | | |
| 72 | Qwen3.5-35B-A3B | Alibaba · Open weight | 19.7% | | |
| 73 | GPT-5 mini | OpenAI · Closed | 19.7% | | |
| 74 | Nemotron 3 Super 120B A12B | NVIDIA · Open weight | 19.2% | | |
| 75 | MiniMax M2.5 | MiniMax · Closed | 19.1% | | |
| 76 | Claude Opus 4.6 | Anthropic · Closed | 18.6% | | |
| 77 | GPT-OSS 120B | OpenAI · Open weight | 18.5% | | |
| 78 | Gemma 4 26B A4B | Google · Open weight | 18.3% | | |
| 79 | Grok 4.1 Fast (Reasoning) | xAI · Closed | 17.6% | | |
| 80 | Gemini 3.5 Flash-Lite | Google · Closed | 17.5% | | |
| 81 | Grok 4 Fast (Reasoning) | xAI · Closed | 17.0% | | |
| 82 | Gemini 3.1 Flash-Lite | Google · Closed | 16.2% | | |
| 83 | GLM-5V-Turbo | Z.AI · Closed | 15.8% | | |
| 84 | Mercury 2 | Inception · Closed | 15.5% | | |
| 85 | DeepSeek-R1 | DeepSeek · Open weight | 14.9% | | |
| 86 | Gemma 4 12B | Google · Open weight | 14.8% | | |
| 87 | Trinity-Large-Preview | Arcee AI · Open weight | 14.7% | | |
| 88 | Trinity-Large-Thinking | Arcee AI · Open weight | 14.7% | | |
| 89 | Gemini 3 Flash | Google · Closed | 14.1% | | |
| 90 | Claude Sonnet 4.6 | Anthropic · Closed | 13.2% | | |
| 91 | K-Exaone | LG AI Research · Closed | 13.1% | | |
| 92 | DeepSeek V3.1 (Reasoning) | DeepSeek · Open weight | 13.0% | | |
| 93 | Claude Opus 4.5 | Anthropic · Closed | 12.9% | | |
| 94 | Mistral Medium 3.5 128B | Mistral · Open weight | 12.8% | | |
| 95 | Claude 4.1 Opus Thinking | Anthropic · Closed | 11.9% | | |
| 96 | Command A+ | Cohere · Open weight | 11.4% | | |
| 97 | Qwen3 Max | Alibaba · Closed | 11.1% | | |
| 98 | DeepSeek V3.2 | DeepSeek · Open weight | 10.5% | | |
| 99 | Nemotron 3 Nano 30B | NVIDIA · Open weight | 10.2% | | |
| 100 | Sarvam 105B | Sarvam · Open weight | 10.1% | | |
| 101 | GPT-OSS 20B | OpenAI · Open weight | 9.8% | | |
| 102 | Mistral Small 4 | Mistral · Open weight | 9.5% | | |
| 103 | Mistral Small 4 (Reasoning) | Mistral · Open weight | 9.5% | | |
| 104 | o3-mini | OpenAI · Closed | 8.7% | | |
| 105 | GPT-5 nano | OpenAI · Closed | 8.2% | | |
| 106 | MiniMax M1 80k | MiniMax · Closed | 8.2% | | |
| 107 | Nemotron Ultra 253B | NVIDIA · Open weight | 8.1% | | |
| 108 | MiMo-V2-Flash | Xiaomi · Open weight | 8.0% | | |
| 109 | o1 | OpenAI · Closed | 7.7% | | |
| 110 | Grok Code Fast 1 | xAI · Closed | 7.5% | | |
| 111 | GLM-4.7-Flash | Z.AI · Open weight | 7.1% | | |
| 112 | Kimi K2 | Moonshot AI · Closed | 7.0% | | |
| 113 | Sarvam 30B | Sarvam · Open weight | 7.0% | | |
| 114 | LFM2.5-8B-A1B | LiquidAI · Open weight | 6.9% | | |
| 115 | GLM-4.5-Air | Z.AI · Closed | 6.8% | | |
| 116 | LFM2.5-1.2B-Instruct | LiquidAI · Closed | 6.8% | | |
| 117 | Granite-4.0-H-350M | IBM · Open weight | 6.4% | | |
| 118 | DeepSeek V3.1 | DeepSeek · Open weight | 6.3% | | |
| 119 | Ling 2.6 Flash | InclusionAI · Open weight | 6.2% | | |
| 120 | LFM2.5-1.2B-Thinking | LiquidAI · Closed | 6.1% | | |
| 121 | Exaone 4.0 1.2B | LG AI Research · Open weight | 5.8% | | |
| 122 | Granite-4.0-350M | IBM · Open weight | 5.7% | | |
| 123 | DeepSeek R1 Distill Qwen 32B | DeepSeek · Open weight | 5.5% | | |
| 124 | Nemotron 3 Nano Omni 30B A3B | NVIDIA · Open weight | 5.3% | | |
| 125 | Ministral 3 3B (Reasoning) | Mistral · Open weight | 5.3% | | |
| 126 | Ministral 3 3B | Mistral · Open weight | 5.3% | | |
| 127 | GLM-4.6 | Z.AI · Open weight | 5.2% | | |
| 128 | Gemini 2.5 Flash | Google · Closed | 5.1% | | |
| 129 | LFM2.5-VL-1.6B-Extract | LiquidAI · Open weight | 5.1% | | |
| 130 | Granite-4.0-1B | IBM · Open weight | 5.1% | | |
| 131 | Grok 4.1 Fast | xAI · Closed | 5.0% | | |
| 132 | Granite-4.0-H-1B | IBM · Open weight | 5.0% | | |
| 133 | Exaone 4.0 32B | LG AI Research · Open weight | 4.9% | | |
| 134 | Gemini 1.5 Pro | Google · Closed | 4.9% | | |
| 135 | Llama 4 Maverick | Meta · Open weight | 4.8% | | |
| 136 | Gemma 4 E2B | Google · Open weight | 4.8% | | |
| 137 | Gemma 3 27B | Google · Open weight | 4.7% | | |
| 138 | GPT-4.1 | OpenAI · Closed | 4.6% | | |
| 139 | GPT-4.1 mini | OpenAI · Closed | 4.6% | | |
| 140 | Gemini 1.0 Pro | Google · Closed | 4.6% | | |
| 141 | Ministral 3 14B (Reasoning) | Mistral · Open weight | 4.6% | | |
| 142 | Ministral 3 14B | Mistral · Open weight | 4.6% | | |
| 143 | LFM2-24B-A2B | LiquidAI · Closed | 4.4% | | |
| 144 | Llama 4 Scout | Meta · Open weight | 4.3% | | |
| 145 | Mistral Medium 3 | Mistral · Closed | 4.3% | | |
| 146 | Ministral 3 8B (Reasoning) | Mistral · Open weight | 4.3% | | |
| 147 | Ministral 3 8B | Mistral · Open weight | 4.3% | | |
| 148 | Llama 3.1 405B | Meta · Open weight | 4.2% | | |
| 149 | Mistral Large 3 | Mistral · Closed | 4.1% | | |
| 150 | Phi-4 | Microsoft · Open weight | 4.1% | | |
| 151 | Claude 4 Sonnet | Anthropic · Closed | 4.0% | | |
| 152 | GPT-4o mini | OpenAI · Closed | 4.0% | | |
| 153 | Mistral Large 2 | Mistral · Closed | 4.0% | | |
| 154 | GPT-4.1 nano | OpenAI · Closed | 3.9% | | |
| 155 | Claude 3 Haiku | Anthropic · Closed | 3.9% | | |
| 156 | Qwen2.5 Coder 32B Instruct | Alibaba · Open weight | 3.8% | | |
| 157 | Solar Pro 2 | Upstage · Closed | 3.8% | | |
| 158 | Gemma 4 E4B | Google · Open weight | 3.7% | | |
| 159 | DeepSeek V3 | DeepSeek · Open weight | 3.6% | | |
| 160 | Nova Pro | Amazon · Closed | 3.4% | | |
| 161 | GPT-4o | OpenAI · Closed | 3.3% | | |
| 162 | GPT-4 Turbo | OpenAI · Closed | 3.3% | | |
| 163 | Claude 3 Opus | Anthropic · Closed | 3.1% | | |