| 1 | Gemini 3.1 Pro | Google | Proprietary | 83.9% | |
| 2 | Gemini 3.5 Flash | Google | Proprietary | 83.6% | |
| 3 | GPT-5.6 Sol | OpenAI | Proprietary | 83% | |
| 4 | Qwen3.8 Max | Alibaba · Open weight | 82.3% | | |
| 5 | Kimi K3 | Moonshot AI · Closed | 81.6% | | |
| 6 | Seed 2.1 Pro | ByteDance · Closed | 81.6% | | |
| 7 | GPT-5.5 | OpenAI · Closed | 81.2% | | |
| 8 | GPT-5.4 | OpenAI · Closed | 81.2% | | |
| 9 | Gemini 3 Pro | Google · Closed | 81% | | |
| 10 | GPT-5.6 Terra | OpenAI · Closed | 80.7% | | |
| 11 | Muse Spark | Meta · Closed | 80.4% | | |
| 12 | Seed 2.1 Turbo | ByteDance · Closed | 80.1% | | |
| 13 | GPT-5.2 | OpenAI · Closed | 79.5% | | |
| 14 | Kimi K2.6 | Moonshot AI · Open weight | 79.4% | | |
| 15 | dots3-note Preview | Dots Studio · Open weight | 79.1% | | |
| 16 | Qwen3.7 Plus | Alibaba · Closed | 79% | | |
| 17 | Qwen3.5 397B | Alibaba · Open weight | 79% | | |
| 18 | Qwen3.6 Plus | Alibaba · Closed | 78.8% | | |
| 19 | Kimi K2.5 | Moonshot AI · Open weight | 78.5% | | |
| 20 | Kimi K2.5 (Reasoning) | Moonshot AI · Closed | 78.5% | | |
| 21 | GPT-5.6 Luna | OpenAI · Closed | 78.4% | | |
| 22 | MiniMax M3 | MiniMax · Open weight | 78.1% | | |
| 23 | Grok 4.3 | xAI · Closed | 78.1% | | |
| 24 | Pareto 26.9 | Unbiased · Closed | 78% | | |
| 25 | MiMo-V2.5 | Xiaomi · Closed | 77.9% | | |
| 26 | Claude Opus 4.6 | Anthropic · Closed | 77.3% | | |
| 27 | Gemma 4 31B | Google · Open weight | 76.9% | | |
| 28 | GPT-5.4 mini | OpenAI · Closed | 76.6% | | |
| 29 | Step 5 Preview | StepFun · Closed | 76% | | |
| 30 | Qwen3.6-27B | Alibaba · Open weight | 75.8% | | |
| 31 | Qwen3.6-35B-A3B | Alibaba · Open weight | 75.3% | | |
| 32 | Grok 4.20 | xAI · Closed | 75.2% | | |
| 33 | Inkling-Small | Thinking Machines Lab · Open weight | 74% | | |
| 34 | Muse Glimmer 30B | Meta · Open weight | 74% | | |
| 35 | Gemma 4 26B A4B | Google · Open weight | 73.8% | | |
| 36 | Inkling | Thinking Machines Lab · Open weight | 73.5% | | |
| 37 | Interfaze Beta | Interfaze · Closed | 71.1% | | |
| 38 | Claude Opus 4.5 | Anthropic · Closed | 70.6% | | |
| 39 | Gemma 4 12B | Google · Open weight | 69.1% | | |
| 40 | GPT-5.4 nano | OpenAI · Closed | 66.1% | | |
| 41 | Command A+ | Cohere · Open weight | 63% | | |
| 42 | LFM2.5-VL-3B | LiquidAI · Open weight | 30.5% | | |