| 1 | Claude Opus 5.5 | Anthropic | Proprietary | 66.9% | |
| 2 | Claude Fable 5.1 | Anthropic | Proprietary | 63.1% | |
| 3 | Claude Fable 5 | Anthropic | Proprietary | 61.0% | |
| 4 | MiMo-V2.6-Pro | Xiaomi · Open weight | 60.9% | | |
| 5 | Kimi K3 | Moonshot AI · Closed | 59.5% | | |
| 6 | GLM-5.3 | Z.AI · Open weight | 59.0% | | |
| 7 | Step 5 Preview | StepFun · Closed | 58.9% | | |
| 8 | Muse Spark 1.1 | Meta · Closed | 58.8% | | |
| 9 | Muse Spark 1.3 | Meta · Closed | 58.8% | | |
| 10 | Gemini 3.1 Pro | Google · Closed | 58.7% | | |
| 11 | GPT-6 Sol | OpenAI · Closed | 57.6% | | |
| 12 | Muse Spark 1.2 | Meta · Closed | 57.4% | | |
| 13 | Grok 4.7 | xAI · Closed | 57.4% | | |
| 14 | Gemini 3.7 Flash | Google · Closed | 57.2% | | |
| 15 | GPT-5.6 Sol | OpenAI · Closed | 57.1% | | |
| 16 | Gemini 3.8 Flash | Google · Closed | 56.6% | | |
| 17 | GPT-6 Astra | OpenAI · Closed | 56.5% | | |
| 18 | Grok 4.6 | xAI · Closed | 56.5% | | |
| 19 | Claude Opus 5 | Anthropic · Closed | 56.4% | | |
| 20 | GPT-5.5 | OpenAI · Closed | 55.8% | | |
| 21 | GPT-5.6 Terra | OpenAI · Closed | 55.0% | | |
| 22 | Grok 4.5 | xAI · Closed | 55.0% | | |
| 23 | GPT-6 Luna | OpenAI · Closed | 54.6% | | |
| 24 | Claude Opus 4.8 | Anthropic · Closed | 54.4% | | |
| 25 | Claude Sonnet 5 | Anthropic · Closed | 54.3% | | |
| 26 | Gemini 3.5 Flash | Google · Closed | 53.9% | | |
| 27 | GPT-5.6 Luna | OpenAI · Closed | 53.6% | | |
| 28 | Gemini 3.6 Flash | Google · Closed | 53.4% | | |
| 29 | GPT-5.4 mini | OpenAI · Closed | 52.1% | | |
| 30 | Qwen3.8 Max Preview | Alibaba · Closed | 52.1% | | |
| 31 | DeepSeek V4.1 Flash | DeepSeek · Open weight | 51.9% | | |
| 32 | Kimi K2.6 | Moonshot AI · Open weight | 51.5% | | |
| 33 | GLM-5.2 | Z.AI · Open weight | 51.2% | | |
| 34 | DeepSeek V4 Pro 0813 | DeepSeek · Closed | 51.0% | | |
| 35 | MiMo-V2.5-Pro | Xiaomi · Closed | 50.6% | | |
| 36 | Qwen3.8-Flash-Next | Alibaba · Open weight | 50.6% | | |
| 37 | DeepSeek V4 Flash 0731 | DeepSeek · Closed | 50.3% | | |
| 38 | MiniMax M2.7 | MiniMax · Open weight | 50.1% | | |
| 39 | Inkling-Small | Thinking Machines Lab · Open weight | 49.7% | | |
| 40 | Qwen3.7 Max | Alibaba · Closed | 49.5% | | |
| 41 | Hy3 | Tencent · Open weight | 48.6% | | |
| 42 | Hy3 Preview | Tencent · Open weight | 48.6% | | |
| 43 | Grok 4.3 | xAI · Closed | 48.3% | | |
| 44 | Quasar 438B | Multiverse Computing · Closed | 48.1% | | |
| 45 | Kimi K2.7 Code | Moonshot AI · Open weight | 47.8% | | |
| 46 | GPT-5.4 nano | OpenAI · Closed | 47.2% | | |
| 47 | MiniMax M3 | MiniMax · Open weight | 47.1% | | |
| 48 | Inkling | Thinking Machines Lab · Open weight | 47.0% | | |
| 49 | Qwen3.8-27B | Alibaba · Open weight | 46.6% | | |
| 51 | Gemini 2.5 Pro | Google · Closed | 46.3% | | |
| 52 | Qwen3.7 Plus | Alibaba · Closed | 46.1% | | |
| 53 | Gemma 4 31B | Google · Open weight | 45.5% | | |
| 54 | Apodex 1.1 | Apodex · Closed | 45.5% | | |
| 55 | Apodex 1.1 Mini | Apodex · Open weight | 45.5% | | |
| 56 | Muse Glimmer 30B | Meta · Open weight | 44.9% | | |
| 57 | GLM-5.1 | Z.AI · Open weight | 44.8% | | |
| 58 | Solar Pro 4 | Upstage · Closed | 44.6% | | |
| 59 | Ling 3.0 Flash VL | InclusionAI · Open weight | 44.2% | | |
| 60 | Step 3.7 Flash | StepFun · Open weight | 43.9% | | |
| 61 | Qwen3.6-27B | Alibaba · Open weight | 42.8% | | |
| 62 | Ling 3.0 Flash | InclusionAI · Open weight | 42.0% | | |
| 63 | Ling 3.0 Flash FP8 | InclusionAI · Open weight | 42.0% | | |
| 64 | K-EXAONE 2.0 | LG AI Research · Open weight | 42.0% | | |
| 65 | Gemini 3.5 Flash-Lite | Google · Closed | 41.3% | | |
| 66 | A.X K2 | SK Telecom · Open weight | 41.0% | | |
| 67 | Trinity-Large-Thinking | Arcee AI · Open weight | 40.6% | | |
| 68 | Trinity-Large-Preview | Arcee AI · Open weight | 40.6% | | |
| 69 | Nemotron 3 Ultra | NVIDIA · Open weight | 40.3% | | |
| 70 | Mistral Medium 3.5 128B | Mistral · Open weight | 40.2% | | |
| 71 | Gemma 4 26B A4B | Google · Open weight | 40.0% | | |
| 72 | Qwen3.5-122B-A10B | Alibaba · Open weight | 39.7% | | |
| 73 | GPT-5 mini | OpenAI · Closed | 39.0% | | |
| 74 | GPT-OSS 20B | OpenAI · Open weight | 38.9% | | |
| 75 | Mistral Small 4 | Mistral · Open weight | 38.8% | | |
| 76 | North Mini Code | Cohere · Open weight | 38.8% | | |
| 77 | Mistral Small 4 (Reasoning) | Mistral · Open weight | 38.8% | | |
| 78 | Command A+ | Cohere · Open weight | 38.5% | | |
| 79 | Granite 4.2 30B | IBM · Open weight | 37.8% | | |
| 80 | Mercury 2 | Inception · Closed | 37.7% | | |
| 81 | Qwen3.6-35B-A3B | Alibaba · Open weight | 36.6% | | |
| 82 | Mistral Large 3 | Mistral · Closed | 36.6% | | |
| 83 | Nemotron 3 Super 100B | NVIDIA · Open weight | 36.2% | | |
| 84 | Nemotron 3 Super 120B A12B | NVIDIA · Open weight | 36.2% | | |
| 85 | DeepSeek V3 | DeepSeek · Open weight | 35.8% | | |
| 86 | GPT-OSS 120B | OpenAI · Open weight | 34.0% | | |
| 87 | Nemotron 3.5 Lightning 30B A3B NVFP4 | NVIDIA · Open weight | 32.1% | | |
| 88 | Llama 4 Maverick | Meta · Open weight | 31.7% | | |
| 89 | Granite 4.2 8B | IBM · Open weight | 31.5% | | |
| 90 | Nemotron 3 Nano 30B | NVIDIA · Open weight | 30.6% | | |
| 91 | MiniCPM5-2B | OpenBMB · Open weight | 26.3% | | |
| 92 | Solar Pro 3 | Upstage · Closed | 25.5% | | |
| 93 | Granite 4.2 3B | IBM · Open weight | 25.3% | | |
| 94 | Ling 3.0 Tiny | InclusionAI · Open weight | 24.2% | | |
| 95 | Ministral 3 14B (Reasoning) | Mistral · Open weight | 23.8% | | |
| 96 | Ministral 3 14B | Mistral · Open weight | 23.8% | | |
| 97 | Gemma 3 27B | Google · Open weight | 23.3% | | |
| 98 | Celeris-1 | Celeris · Closed | 21.6% | | |
| 99 | Llama 4 Scout | Meta · Open weight | 21.3% | | |
| 100 | Ministral 3 8B (Reasoning) | Mistral · Open weight | 20.7% | | |
| 101 | Ministral 3 8B | Mistral · Open weight | 20.7% | | |
| 102 | Ministral 3 3B (Reasoning) | Mistral · Open weight | 15.3% | | |
| 103 | Ministral 3 3B | Mistral · Open weight | 15.3% | | |
| 104 | LFM2.5-2.6B | LiquidAI · Open weight | 14.4% | | |