YZ Index
评测数据
当前展示:Run #398 | 2026-10-27 | 128 题库 | 公式 v7 | 判分 v6.5
数据公开说明:为防止题库污染和过拟合,题目原文和预期答案不公开。本页展示模型回答、得分、判分方式等透明数据。完整方法论请参阅方法论页面。
| 模型 | 代码执行 | 材料约束 | 工程判断 | 任务表达 | 诚信 | 主榜分 | 性价比 | 稳定性 | 可用性 | 逐题 |
|---|---|---|---|---|---|---|---|---|---|---|
| Claude Opus 4.7 claude | 99.80 | 72.90 | 63.90 | 87.50 | 100.00 pass | 87.70 | 27.9 | 50.5 | 100.0 | |
| GPT-5.5 gpt | 100.00 | 52.20 | 75.00 | 100.00 | 90.00 pass | 78.49 | 74.7 | 37.7 | 100.0 | |
| Gemini 3.1 Pro gemini | 75.00 | 80.20 | 50.00 | 75.00 | 90.00 pass | 77.34 | 85.1 | 20.9 | 100.0 | |
| GPT-6 Astra gpt | 100.00 | 48.10 | 75.00 | 94.70 | 90.00 pass | 76.65 | 37.4 | 38.5 | 100.0 | |
| Claude Sonnet 4.6 claude | 99.80 | 48.10 | 67.90 | 70.00 | 90.00 pass | 76.54 | 84.9 | 36.1 | 100.0 | |
| GPT-6 Luna gpt | 100.00 | 38.80 | 75.00 | 91.30 | 90.00 pass | 72.46 | 100.0 | 33.0 | 100.0 | |
| Grok 4 grok | 94.60 | 45.00 | 30.60 | 71.30 | 90.00 pass | 72.28 | 81.3 | 15.1 | 100.0 | |
| GPT-6.1 Sol gpt | 75.00 | 48.10 | 75.00 | 94.70 | 90.00 pass | 62.90 | 93.4 | 29.7 | 100.0 | |
| GPT-6 Sol gpt | 75.00 | 45.90 | 50.00 | 94.70 | 90.00 pass | 61.91 | 92.2 | 23.4 | 100.0 | |
| GPT-o3 gpt | 50.00 | 72.90 | 75.00 | 71.30 | 80.00 pass | 60.31 | 35.1 | 36.7 | 90.0 | |
| DeepSeek V4 Pro deepseek | 50.00 | 65.20 | 50.00 | 75.00 | 90.00 pass | 56.84 | 93.8 | 59.3 | 75.0 | |
| Gemini 2.5 Pro gemini | 50.00 | 61.10 | 50.00 | 77.50 | 100.00 pass | 55.00 | 91.0 | 30.5 | 90.0 | |
| 豆包 Pro doubao | 25.00 | 70.20 | 75.00 | 93.80 | 100.00 pass | 45.34 | 100.0 | 35.4 | 90.0 | |
| GLM-4.6 zhipu | 25.00 | - | - | - | - | - | 100.0 | 75.0 | 25.0 | |
| Qwen3 Max qwen | - | - | - | - | - | - | 0.0 | 75.0 | 0.0 |
API 访问:如需程序化访问评测数据,请使用我们的 API。