YZ Index
评测数据
当前展示:Run #385 | 2026-10-19 | 128 题库 | 公式 v7 | 判分 v6.4
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-5.5 gpt | 97.00 | 89.30 | 75.00 | 100.00 | 90.00 pass | 93.54 | 80.5 | 51.7 | 100.0 | |
| Grok 4 grok | 95.30 | 89.30 | 30.60 | 75.00 | 70.00 pass | 92.60 | 87.6 | 26.0 | 100.0 | |
| GPT-6 Astra gpt | 97.00 | 64.40 | 75.00 | 100.00 | 80.00 pass | 82.33 | 39.5 | 46.0 | 100.0 | |
| GPT-6 Sol gpt | 97.00 | 64.40 | 75.00 | 100.00 | 90.00 pass | 82.33 | 97.1 | 46.7 | 100.0 | |
| GPT-6.1 Sol gpt | 97.00 | 64.40 | 75.00 | 100.00 | 80.00 pass | 82.33 | 97.0 | 46.0 | 100.0 | |
| GPT-6 Luna gpt | 97.00 | 61.80 | 55.60 | 95.00 | 80.00 pass | 81.16 | 100.0 | 36.2 | 100.0 | |
| Claude Opus 4.7 claude | 72.00 | 89.30 | 61.10 | 60.00 | 90.00 pass | 79.79 | 27.7 | 28.4 | 100.0 | |
| 豆包 Pro doubao | 72.00 | 77.60 | 75.00 | 100.00 | 70.00 pass | 74.52 | 100.0 | 46.6 | 95.0 | |
| Claude Sonnet 4.6 claude | 71.60 | 77.60 | 61.10 | 95.00 | 65.00 pass | 74.30 | 87.8 | 28.2 | 100.0 | |
| Gemini 2.5 Pro gemini | 74.30 | 65.10 | 25.00 | 85.00 | 90.00 pass | 70.16 | 92.8 | 34.6 | 90.0 | |
| Gemini 3.1 Pro gemini | 47.00 | 77.60 | 50.00 | 100.00 | 90.00 pass | 60.77 | 72.2 | 21.1 | 100.0 | |
| GPT-o3 gpt | 47.00 | 65.10 | 100.00 | 75.00 | 65.00 pass | 55.15 | 28.6 | 44.1 | 85.0 | |
| DeepSeek V4 Pro deepseek | 47.00 | 52.60 | 75.00 | 75.00 | 70.00 pass | 49.52 | 85.9 | 34.0 | 85.0 | |
| GLM-4.6 zhipu | 47.00 | 50.00 | 0.00 | 25.00 | 65.00 pass | 48.35 | 71.2 | 21.5 | 50.0 | |
| 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。