| 3 | Moonshot AI | OpenHands | Kimi K3 | kimi/kimi-k3 | |
| 4 | Claude Opus 4.8 | Anthropic | OpenHands | 82.72% | |
| 5 | Claude Sonnet 5 | Anthropic | OpenHands | 81.33% | |
| 6 | GPT-5.6 Sol | OpenAI | OpenHands | 80.50% | |
| 7 | Claude Opus 4.8 Claude Code | Anthropic | Claude Code | 77.48% | |
| 8 | GPT-5.6 Luna | OpenAI | OpenHands | 77.06% | |
| 9 | Muse Spark 1.1 | Meta | OpenHands | 72.16% | |
| 10 | Claude Opus 4.7 | Anthropic | OpenHands | 71.00% | |
| 11 | GPT-5.5 | OpenAI | OpenHands | 69.85% | |
| 12 | Grok 4.5 | xAI | OpenHands | 69.00% | |
| 13 | GPT-5.6 Terra | OpenAI | OpenHands | 67.84% | |
| 14 | GPT-5.4 | OpenAI | OpenHands | 67.42% | |
| 15 | GPT-5.5 Factory | OpenAI | Factory | 67.39% | |
| 16 | GLM 5.2 | Zhipu AI | OpenHands | 63.96% | |
| 17 | GPT-5.3 Codex | OpenAI | OpenHands | 61.77% | |
| 18 | GPT-5.5 Codex | OpenAI | Codex | 58.19% | |
| 19 | Claude Opus 4.6 | Anthropic | OpenHands | 57.57% | |
| 20 | Gemini 3.6 Flash | Google | OpenHands | 57.32% | |
| 21 | Claude Sonnet 4.6 Claude Code | Anthropic | Claude Code | 55.77% | |
| 22 | GPT-5.2 | OpenAI | OpenHands | 53.50% | |
| 23 | Claude Opus 4.6 Thinking | Anthropic | OpenHands | 53.50% | |
| 24 | Claude Sonnet 4.6 | Anthropic | OpenHands | 51.48% | |
| 25 | DeepSeek V4 Pro | DeepSeek | OpenHands | 49.93% | |
| 26 | Composer 2.5 | Cursor | Cursor CLI | 49.61% | |
| 27 | Gemini 3.5 Flash | Google | OpenHands | 48.68% | |
| 28 | GPT-5.4 | OpenAI | Codex | 48.47% | |
| 29 | GPT-5.4 Mini | OpenAI | OpenHands | 47.97% | |
| 30 | Qwen3.7 Max | Alibaba | OpenHands | 47.67% | |
| 31 | MiniMax M3 | MiniMax | OpenHands | 47.57% | |
| 32 | Kimi K2.7 Code | Moonshot AI | OpenHands | 47.21% | |
| 33 | Qwen3.7 Plus | Alibaba | OpenHands | 46.39% | |
| 34 | Mimo V2.5 | Xiaomi | OpenHands | 42.17% | |
| 35 | GPT-5.2 Codex | OpenAI | OpenHands | 37.91% | |
| 36 | Kimi K2.6 | Moonshot AI | OpenHands | 37.89% | |
| 37 | Gemini 3.5 Flash Lite | Google | OpenHands | 37.16% | |
| 38 | Mimo V2.5 Pro | Xiaomi | OpenHands | 34.11% | |
| 39 | Gemini 3.1 Pro Preview | Google | OpenHands | 32.03% | |
| 40 | GLM 5.1 | Zhipu AI | OpenHands | 31.46% | |
| 41 | GPT-5.4 Nano | OpenAI | OpenHands | 26.10% | |
| 42 | Qwen3.6 Plus | Alibaba | OpenHands | 25.57% | |
| 43 | GPT-5.1 | OpenAI | OpenHands | 24.61% | |
| 44 | GLM 5 Thinking | Zhipu AI | OpenHands | 23.36% | |
| 45 | Claude Sonnet 4.5 20250929 Thinking | Anthropic | OpenHands | 22.62% | |
| 46 | GPT-5.1 Codex Max | OpenAI | OpenHands | 22.17% | |
| 47 | Claude Opus 4.5 20251101 Thinking | Anthropic | OpenHands | 20.63% | |
| 48 | Gemini 3 Flash Preview | Google | OpenHands | 20.20% | |
| 49 | GPT-5 | OpenAI | OpenHands | 20.09% | |
| 50 | Muse Spark | Meta | OpenHands | 19.67% | |
| 51 | Grok 4.3 | xAI | OpenHands | 19.40% | |
| 52 | Inkling | Thinkingmachines | OpenHands | 19.21% | |
| 53 | Kimi K2.5 Thinking | Moonshot AI | OpenHands | 17.54% | |
| 54 | Qwen3.5 Plus Thinking | Alibaba | OpenHands | 15.74% | |
| 55 | MiniMax M2.5 | MiniMax | OpenHands | 14.85% | |
| 56 | Gemini 3 Pro Preview | Google | OpenHands | 14.30% | |
| 57 | GPT-5 Mini | OpenAI | OpenHands | 14.17% | |
| 58 | Grok Build 0.1 | xAI | Grok Build | 13.35% | |
| 59 | GPT-5.1 Codex | OpenAI | OpenHands | 13.12% | |
| 60 | Qwen3.6 27b | Alibaba | OpenHands | 11.94% | |
| 61 | MiniMax M2.7 | MiniMax | OpenHands | 11.93% | |
| 62 | Claude Haiku 4.5 20251001 Thinking | Anthropic | OpenHands | 11.39% | |
| 63 | Laguna M.1 | Poolside | OpenHands | 11.04% | |
| 64 | Nemotron 3 Ultra 550b A55b | Nvidia | OpenHands | 7.64% | |
| 65 | Swe 1.6 Fast | Devin | Devin CLI | 7.22% | |
| 66 | Laguna Xs.2 | Poolside | OpenHands | 5.21% | |
| 67 | DeepSeek V3p2 Thinking | Fireworks AI | OpenHands | 5.11% | |
| 68 | Grok 4.20 0309 Reasoning | xAI | OpenHands | 4.06% | |
| 69 | Qwen3 Max | Alibaba | OpenHands | 3.51% | |
| 70 | GLM 4.6 | Zhipu AI | OpenHands | 3.09% | |
| 71 | Mistral Medium 3.5 | Mistral AI | OpenHands | 2.89% | |
| 72 | Grok 4.1 Fast Reasoning | xAI | OpenHands | 1.20% | |
| 73 | Gemini 2.5 Pro | Google | OpenHands | 0.40% | |
| 74 | Gemini 3.1 Flash Lite Preview | Google | OpenHands | 0.00% | |
| 75 | Grok 4 Fast Reasoning | xAI | OpenHands | 0.00% | |
| 76 | Mistral Small 2603 | Mistral AI | OpenHands | 0.00% | |