YZ Index
评测数据
当前展示:Run #399 | 2026-10-28 | 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 |
|---|---|---|---|---|---|---|---|---|---|---|
| GPT-6 Luna gpt | 100.00 | 71.00 | 100.00 | 87.50 | 80.00 pass | 86.95 | 100.0 | 55.5 | 100.0 | |
| GPT-6 Astra gpt | 100.00 | 64.30 | 100.00 | 87.50 | 80.00 pass | 83.94 | 40.0 | 47.4 | 100.0 | |
| GPT-6 Sol gpt | 100.00 | 64.30 | 100.00 | 87.50 | 80.00 pass | 83.94 | 97.2 | 47.4 | 100.0 | |
| GPT-6.1 Sol gpt | 100.00 | 64.30 | 100.00 | 87.50 | 80.00 pass | 83.94 | 97.2 | 47.4 | 100.0 | |
| 豆包 Pro doubao | 75.00 | 81.70 | 100.00 | 91.70 | 90.00 pass | 78.02 | 100.0 | 61.7 | 95.0 | |
| GPT-o3 gpt | 75.00 | 81.70 | 100.00 | 87.90 | 80.00 pass | 78.02 | 44.4 | 59.6 | 95.0 | |
| Grok 4 grok | 74.40 | 75.00 | 62.00 | 77.90 | 65.00 pass | 74.67 | 82.6 | 24.9 | 100.0 | |
| GPT-5.5 gpt | 75.00 | 71.00 | 100.00 | 91.70 | 80.00 pass | 73.20 | 72.4 | 57.1 | 95.0 | |
| Claude Opus 4.7 claude | 75.00 | 56.70 | 100.00 | 60.40 | 100.00 pass | 66.77 | 23.0 | 30.7 | 100.0 | |
| Claude Sonnet 4.6 claude | 74.80 | 56.70 | 100.00 | 56.30 | 80.00 pass | 66.66 | 85.5 | 27.3 | 100.0 | |
| Gemini 2.5 Pro gemini | 50.00 | 64.30 | 75.00 | 85.40 | 90.00 pass | 56.44 | 92.5 | 47.4 | 85.0 | |
| DeepSeek V4 Pro deepseek | 25.00 | 71.00 | 100.00 | 91.70 | 80.00 pass | 45.70 | 92.5 | 55.5 | 85.0 | |
| Gemini 3.1 Pro gemini | 25.00 | 71.00 | 75.00 | 91.70 | 80.00 pass | 45.70 | 70.8 | 20.4 | 100.0 | |
| GLM-4.6 zhipu | 25.00 | 71.00 | 58.30 | 66.70 | 90.00 pass | 45.70 | 89.5 | 48.4 | 75.0 | |
| 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。