YZ Index
评测数据
当前展示:Run #405 | 2026-11-01 | 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 | 97.80 | 100.00 | 33.30 | 47.90 | 100.00 pass | 98.79 | 27.9 | 23.1 | 100.0 | |
| GPT-6 Astra gpt | 95.00 | 100.00 | 75.00 | 87.50 | 90.00 pass | 97.25 | 43.4 | 50.4 | 100.0 | |
| GPT-6 Luna gpt | 94.30 | 86.80 | 75.00 | 58.80 | 90.00 pass | 90.93 | 100.0 | 41.2 | 100.0 | |
| Claude Sonnet 4.6 claude | 95.60 | 75.10 | 25.00 | 62.50 | 90.00 pass | 86.38 | 85.6 | 22.9 | 100.0 | |
| GPT-6.1 Sol gpt | 95.00 | 75.00 | 75.00 | 87.50 | 90.00 pass | 86.00 | 97.2 | 37.2 | 100.0 | |
| GPT-6 Sol gpt | 94.30 | 75.00 | 75.00 | 87.50 | 90.00 pass | 85.62 | 97.1 | 37.4 | 100.0 | |
| Grok 4 grok | 78.20 | 88.30 | 22.20 | 70.40 | 80.00 pass | 82.75 | 84.7 | 31.4 | 100.0 | |
| GPT-o3 gpt | 89.10 | 63.30 | 100.00 | 66.70 | 100.00 pass | 77.49 | 44.8 | 50.6 | 95.0 | |
| GPT-5.5 gpt | 75.00 | 61.80 | 75.00 | 91.70 | 90.00 pass | 69.06 | 71.1 | 27.3 | 100.0 | |
| GLM-4.6 zhipu | 50.00 | 75.00 | 25.00 | 25.00 | 75.00 pass | 61.25 | 93.1 | 42.5 | 55.0 | |
| Gemini 3.1 Pro gemini | 70.00 | 50.00 | 50.00 | 91.70 | 100.00 pass | 61.00 | 81.7 | 14.9 | 100.0 | |
| 豆包 Pro doubao | 78.80 | 36.80 | 75.00 | 76.70 | 90.00 pass | 59.90 | 100.0 | 26.0 | 100.0 | |
| DeepSeek V4 Pro deepseek | 50.00 | 50.10 | 50.00 | 81.30 | 100.00 pass | 50.05 | 94.4 | 31.7 | 85.0 | |
| Gemini 2.5 Pro gemini | 50.00 | 50.00 | 50.00 | 70.40 | 90.00 pass | 50.00 | 90.7 | 24.0 | 85.0 | |
| 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。