| 1 | GPT-5.4 Pro | OpenAI | Closed | gpt-5-4-pro | |
| 2 | Gemini 3.1 Pro | Google | Closed | gemini-3-1-pro | |
| 3 | Gemini 3.5 Flash | Google | Closed | gemini-3-5-flash | |
| 4 | GPT-5.6 Sol | OpenAI · Closed | 83% | | |
| 5 | Kimi K3 | Moonshot AI · Closed | 81.6% | | |
| 6 | GPT-5.5 | OpenAI · Closed | 81.2% | | |
| 7 | GPT-5.4 | OpenAI · Closed | 81.2% | | |
| 8 | Gemini 3 Pro | Google · Closed | 81% | | |
| 9 | GPT-5.6 Terra | OpenAI · Closed | 80.7% | | |
| 10 | Muse Spark | Meta · Closed | 80.4% | | |
| 11 | GPT-5.2 | OpenAI · Closed | 79.5% | | |
| 12 | Kimi K2.6 | Moonshot AI · Open weight | 79.4% | | |
| 13 | Qwen3.7 Plus | Alibaba · Closed | 79% | | |
| 14 | Qwen3.5 397B | Alibaba · Open weight | 79% | | |
| 15 | Qwen3.6 Plus | Alibaba · Closed | 78.8% | | |
| 16 | Kimi K2.5 | Moonshot AI · Open weight | 78.5% | | |
| 17 | Kimi K2.5 (Reasoning) | Moonshot AI · Closed | 78.5% | | |
| 18 | GPT-5.6 Luna | OpenAI · Closed | 78.4% | | |
| 19 | MiniMax M3 | MiniMax · Open weight | 78.1% | | |
| 20 | Grok 4.3 | xAI · Closed | 78.1% | | |
| 21 | MiMo-V2.5 | Xiaomi · Closed | 77.9% | | |
| 22 | Claude Opus 4.6 | Anthropic · Closed | 77.3% | | |
| 23 | Gemma 4 31B | Google · Open weight | 76.9% | | |
| 24 | GPT-5.4 mini | OpenAI · Closed | 76.6% | | |
| 25 | Qwen3.6-27B | Alibaba · Open weight | 75.8% | | |
| 26 | Qwen3.6-35B-A3B | Alibaba · Open weight | 75.3% | | |
| 27 | Grok 4.20 | xAI · Closed | 75.2% | | |
| 28 | Gemma 4 26B A4B | Google · Open weight | 73.8% | | |
| 29 | Inkling | Thinking Machines Lab · Open weight | 73.5% | | |
| 30 | Interfaze Beta | Interfaze · Closed | 71.1% | | |
| 31 | Claude Opus 4.5 | Anthropic · Closed | 70.6% | | |
| 32 | Gemma 4 12B | Google · Open weight | 69.1% | | |
| 33 | GPT-5.4 nano | OpenAI · Closed | 66.1% | | |
| 34 | Command A+ | Cohere · Open weight | 63% | | |