| 1 | OpenAI: o1-pro | openrouter | 97.0 | 97.0 |
| 2 | o3 | openai | 96.0 | 96.0 |
| 3 | GPT-5 | openai | 95.0 | 95.0 |
| 4 | GPT-5 | openai | 95.0 | 95.0 |
| 5 | o1 | openai | 95.0 | 95.0 |
| 6 | OpenAI: o1 | openrouter | 95.0 | 95.0 |
| 7 | o1 | openai | 95.0 | 95.0 |
| 8 | Claude Sonnet 4 | anthropic | 92.0 | 92.0 |
| 9 | DeepSeek: R1 | openrouter | 91.0 | 91.0 |
| 10 | o4-mini | openai | 90.0 | 90.0 |
| 11 | DeepSeek R1 (NetMind) | netmind | 88.0 | 88.0 |
| 12 | o3-mini | openai | 85.0 | 85.0 |
| 13 | Anthropic: Claude 3.7 Sonnet (thinking) | openrouter | 85.0 | 85.0 |
| 14 | o1-mini | openai | 80.0 | 80.0 |
| 15 | xAI: Grok 4.20 Beta | openrouter | 80.0 | 80.0 |
| 16 | xAI: Grok 4.20 Multi-Agent Beta | openrouter | 80.0 | 80.0 |
| 17 | Qwen: Qwen3 Max Thinking | openrouter | 77.0 | 77.0 |
| 18 | OpenAI: o3 Mini High | openrouter | 77.0 | 77.0 |
| 19 | DeepSeek R1 Distill Llama 70B | huggingface | 74.0 | 74.0 |
| 20 | Qwen: Qwen3 VL 235B A22B Thinking | openrouter | 74.0 | 74.0 |
| 21 | Grok 3 Mini | xai | 72.0 | 72.0 |
| 22 | QwQ 32B | huggingface | 72.0 | 72.0 |
| 23 | MoonshotAI: Kimi K2 Thinking | openrouter | 72.0 | 72.0 |
| 24 | DeepSeek: R1 0528 | openrouter | 72.0 | 72.0 |
| 25 | Qwen: Qwen3 VL 30B A3B Thinking | openrouter | 70.0 | 70.0 |
| 26 | TNG: DeepSeek R1T2 Chimera | openrouter | 68.0 | 68.0 |
| 27 | DeepSeek: R1 Distill Llama 70B | openrouter | 68.0 | 68.0 |
| 28 | Qwen3 8B (NetMind) | netmind | 65.0 | 65.0 |
| 29 | Baidu: ERNIE 4.5 21B A3B Thinking | openrouter | 62.0 | 62.0 |
| 30 | Qwen: Qwen3 30B A3B Thinking 2507 | openrouter | 62.0 | 62.0 |
| 31 | DeepSeek: R1 Distill Qwen 32B | openrouter | 61.0 | 61.0 |
| 32 | Qwen: Qwen Plus 0728 (thinking) | openrouter | 61.0 | 61.0 |
| 33 | DeepSeek R1 | netmind | 60.0 | 60.0 |
| 34 | Claude Sonnet 5 (NetMind) | netmind | 57.0 | 57.0 |
| 35 | Qwen: Qwen3 Next 80B A3B Thinking | semantic-cache | 55.0 | 55.0 |
| 36 | o3-mini | semantic-cache | 55.0 | 55.0 |
| 37 | Qwen: Qwen3 235B A22B Thinking 2507 | openrouter | 54.0 | 54.0 |
| 38 | LiquidAI: LFM2.5-1.2B-Thinking (free) | openrouter | 51.0 | 51.0 |
| 39 | Qwen: Qwen3 4B (free) | openrouter | 51.0 | 51.0 |
| 40 | Kimi K2 Thinking | fireworks | 50.0 | 50.0 |
| 41 | Qwen3.5-27B | novita | 50.0 | 50.0 |
| 42 | MiniMax-M2 | novita | 50.0 | 50.0 |
| 43 | GLM 4.6 | novita | 50.0 | 50.0 |
| 44 | MiniMax M2.5 | novita | 50.0 | 50.0 |
| 45 | XiaomiMiMo/MiMo-V2-Flash | novita | 50.0 | 50.0 |
| 46 | Deepseek V3.2 Exp | novita | 50.0 | 50.0 |
| 47 | Qwen3 VL 235B A22B Thinking | novita | 50.0 | 50.0 |
| 48 | GLM 4.6V | novita | 50.0 | 50.0 |
| 49 | Qwen3 Next 80B A3B Instruct | novita | 50.0 | 50.0 |
| 50 | Qwen3 Next 80B A3B Thinking | novita | 50.0 | 50.0 |