YZ Index
评测数据
当前展示:Run #436 | 2026-11-20 | 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 |
|---|---|---|---|---|---|---|---|---|---|---|
| 豆包 Pro doubao | 98.50 | 86.30 | 100.00 | 86.70 | 90.00 pass | 93.01 | 100.0 | 71.9 | 100.0 | |
| Claude Opus 4.7 claude | 94.50 | 89.30 | 100.00 | 61.70 | 100.00 pass | 92.16 | 29.5 | 52.6 | 100.0 | |
| GPT-6 Astra gpt | 96.80 | 79.30 | 97.80 | 67.20 | 80.00 pass | 88.93 | 41.0 | 59.0 | 100.0 | |
| Gemini 2.5 Pro gemini | 75.00 | 86.30 | 100.00 | 86.70 | 80.00 pass | 80.09 | 97.4 | 68.1 | 95.0 | |
| GPT-6 Sol gpt | 71.80 | 84.00 | 97.80 | 72.20 | 90.00 pass | 77.29 | 96.2 | 49.0 | 100.0 | |
| Grok 4 grok | 66.70 | 84.00 | 75.00 | 86.70 | 70.00 pass | 74.49 | 84.3 | 39.8 | 100.0 | |
| GPT-6.1 Sol gpt | 71.80 | 74.00 | 97.80 | 72.50 | 80.00 pass | 72.79 | 95.3 | 45.7 | 100.0 | |
| GPT-5.5 gpt | 71.80 | 73.10 | 100.00 | 81.70 | 80.00 pass | 72.39 | 72.0 | 47.4 | 100.0 | |
| Claude Sonnet 4.6 claude | 70.90 | 73.10 | 100.00 | 70.00 | 80.00 pass | 71.89 | 84.3 | 37.5 | 100.0 | |
| GLM-4.6 zhipu | 47.00 | 86.30 | 75.00 | 25.00 | 65.00 pass | 64.69 | 94.4 | 70.4 | 65.0 | |
| DeepSeek V4 Pro deepseek | 47.00 | 74.00 | 75.00 | 76.40 | 90.00 pass | 59.15 | 95.5 | 65.4 | 85.0 | |
| GPT-o3 gpt | 45.50 | 73.10 | 97.00 | 81.70 | 90.00 pass | 57.92 | 36.9 | 47.8 | 95.0 | |
| GPT-6 Luna gpt | 44.60 | 69.80 | 94.80 | 77.50 | 80.00 pass | 55.94 | 100.0 | 30.2 | 100.0 | |
| Gemini 3.1 Pro gemini | 29.50 | 86.30 | 100.00 | 76.70 | 90.00 pass | 55.06 | 82.1 | 30.8 | 100.0 | |
| 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。