评测来源/Vibe Code Bench v1.1
观察中编程
Vibe Code Bench v1.1
Vals AI · Vibe Code Bench v1.1 的公开模型评测结果。
本来源的模型成绩
| Claude Sonnet 5.5 | 92.39 | 92.4 | 2026-11-05 |
| Gemini 4 Argon | 91.91 | 91.9 | 2026-11-05 |
| Claude Haiku 5.5 | 90.44 | 90.4 | 2026-11-05 |
| Claude Fable 5 | 90.35 | 90.3 | 2026-11-05 |
| Claude Opus 5.5 | 90.29 | 90.3 | 2026-11-05 |
| Claude Fable 5.1 | 90.26 | 90.3 | 2026-11-05 |
| GPT-6 Astra | 89.59 | 89.6 | 2026-11-05 |
| GPT-6.1 Sol | 88.93 | 88.9 | 2026-11-05 |
| Claude Opus 5 | 88.4 | 88.4 | 2026-11-05 |
| GPT-6 Sol | 87.82 | 87.8 | 2026-11-05 |
| DeepSeek V4.1 Flash 1017 | 87.73 | 87.7 | 2026-11-05 |
| Grok 4.7 | 86.17 | 86.2 | 2026-11-05 |
| Muse Spark 1.3 | 85.86 | 85.9 | 2026-11-05 |
| MiMo V2.6 Pro | 85.22 | 85.2 | 2026-11-05 |
| Kimi K3 | 84.97 | 85.0 | 2026-11-05 |
| DeepSeek V4.1 Flash | 84.74 | 84.7 | 2026-11-05 |
| GPT-6.1 Terra | 84 | 84.0 | 2026-11-05 |
| Claude Opus 4.8 | 82.72 | 82.7 | 2026-11-05 |
| DeepSeek V4 Pro 0813 | 82.3 | 82.3 | 2026-11-05 |
| GPT-6 Luna | 81.65 | 81.7 | 2026-11-05 |
| Mistral Large 4 | 81.56 | 81.6 | 2026-11-05 |
| Claude Sonnet 5 | 81.33 | 81.3 | 2026-11-05 |
| GPT-5.6 Sol | 80.5 | 80.5 | 2026-11-05 |
| Muse Spark 1.2 | 79.1 | 79.1 | 2026-11-05 |
| MiMo V2.6 Flash | 78.96 | 79.0 | 2026-11-05 |
| Gemini 3.8 Flash | 78.65 | 78.7 | 2026-11-05 |
| GLM 5.3 | 78.13 | 78.1 | 2026-11-05 |
| GPT-5.6 Luna | 77.06 | 77.1 | 2026-11-05 |
| Grok 4.6 | 76.24 | 76.2 | 2026-11-05 |
| DeepSeek V4 Flash 0731 | 74.74 | 74.7 | 2026-11-05 |
| GPT-5.6 Terra | 74.59 | 74.6 | 2026-11-05 |
| MiniMax M3.1 Flash | 73.94 | 73.9 | 2026-11-05 |
| Muse Spark 1.1 | 72.16 | 72.2 | 2026-11-05 |
| Claude Opus 4.7 | 71 | 71.0 | 2026-11-05 |
| Step 5 Preview | 70.4 | 70.4 | 2026-11-05 |
| GPT-5.5 | 69.85 | 69.8 | 2026-11-05 |
| Grok 4.5 | 69 | 69.0 | 2026-11-05 |
| GPT-5.4 | 67.42 | 67.4 | 2026-11-05 |
| Qwen3.8 Max | 64.7 | 64.7 | 2026-11-05 |
| Gemini 3.6 Flash | 64 | 64.0 | 2026-11-05 |
| GLM-5.2 | 63.96 | 64.0 | 2026-11-05 |
| Claude Sonnet 4.6 | 55.77 | 55.8 | 2026-11-05 |
| GPT-5.2 | 53.5 | 53.5 | 2026-11-05 |
| Claude Opus 4.6 | 53.5 | 53.5 | 2026-11-05 |
| GPT-5.4 mini | 47.97 | 48.0 | 2026-11-05 |
| Qwen3.7 Max | 47.67 | 47.7 | 2026-11-05 |
| MiniMax-M3 | 47.57 | 47.6 | 2026-11-05 |
| Kimi K2.7 Code | 47.21 | 47.2 | 2026-11-05 |
| Qwen3.7 Plus | 46.39 | 46.4 | 2026-11-05 |
| MiMo-V2.5 | 42.17 | 42.2 | 2026-11-05 |
| Kimi K2.6 | 37.89 | 37.9 | 2026-11-05 |
| Gemini 3.5 Flash Lite | 37.16 | 37.2 | 2026-11-05 |
| MiMo-V2.5-Pro | 34.11 | 34.1 | 2026-11-05 |
| GLM-5.1 | 31.46 | 31.5 | 2026-11-05 |
| GLM-5.3 Flash | 30.76 | 30.8 | 2026-11-05 |
| Qwen3.6 Plus | 25.57 | 25.6 | 2026-11-05 |
| GLM-5 | 23.36 | 23.4 | 2026-11-05 |
| Claude Sonnet 4.5 | 22.62 | 22.6 | 2026-11-05 |
| Claude Opus 4.5 | 20.63 | 20.6 | 2026-11-05 |
| GPT-5 | 20.09 | 20.1 | 2026-11-05 |
| Grok 4.3 | 19.4 | 19.4 | 2026-11-05 |
| Inkling | 19.21 | 19.2 | 2026-11-05 |
| Inkling Small | 19.05 | 19.1 | 2026-11-05 |
| Kimi K2.5 | 17.54 | 17.5 | 2026-11-05 |
| Qwen3.5 Plus | 15.74 | 15.7 | 2026-11-05 |
| MiniMax-M2.5 | 14.85 | 14.8 | 2026-11-05 |
| GPT-5 mini | 14.17 | 14.2 | 2026-11-05 |
| Grok Build 0.1 | 13.35 | 13.3 | 2026-11-05 |
| Qwen3.6 27B | 11.94 | 11.9 | 2026-11-05 |
| MiniMax-M2.7 | 11.93 | 11.9 | 2026-11-05 |
| Claude Haiku 4.5 | 11.39 | 11.4 | 2026-11-05 |
| Laguna M.1 | 11.04 | 11.0 | 2026-11-05 |
| Laguna XS.2 | 5.21 | 5.2 | 2026-11-05 |
| DeepSeek V3.2 | 5.11 | 5.1 | 2026-11-05 |
| Grok 4.20 (Reasoning) | 4.06 | 4.1 | 2026-11-05 |
| Qwen3 Max | 3.51 | 3.5 | 2026-11-05 |
| GLM-4.6 | 3.09 | 3.1 | 2026-11-05 |
| Ling-3.0-flash (free) | 2.91 | 2.9 | 2026-11-05 |
| Gemini 2.5 Pro | 0.4 | 0.4 | 2026-11-05 |
| Gemini 3.1 Flash Lite Preview | 0 | 0.0 | 2026-11-05 |