YZ Index
评测数据
当前展示:Run #426 | 2026-11-14 | 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 | 94.50 | 70.00 | 55.60 | 37.50 | 100.00 pass | 83.48 | 24.9 | 25.1 | 100.0 | |
| GPT-6 Luna gpt | 94.50 | 54.80 | 75.00 | 100.00 | 90.00 pass | 76.64 | 100.0 | 41.1 | 100.0 | |
| GPT-5.5 gpt | 94.50 | 54.30 | 75.00 | 100.00 | 90.00 pass | 76.41 | 73.9 | 42.8 | 100.0 | |
| 豆包 Pro doubao | 94.50 | 47.60 | 75.00 | 100.00 | 100.00 pass | 73.40 | 100.0 | 40.2 | 100.0 | |
| GPT-6.1 Sol gpt | 94.50 | 44.80 | 75.00 | 93.80 | 80.00 pass | 72.14 | 95.2 | 37.5 | 100.0 | |
| Claude Sonnet 4.6 claude | 94.50 | 41.40 | 75.00 | 37.50 | 90.00 pass | 70.61 | 81.1 | 25.3 | 100.0 | |
| Grok 4 grok | 88.80 | 44.80 | 50.00 | 93.80 | 70.00 pass | 69.00 | 81.4 | 37.8 | 100.0 | |
| GPT-6 Sol gpt | 91.30 | 34.80 | 75.00 | 96.30 | 80.00 pass | 65.88 | 94.1 | 33.5 | 100.0 | |
| GPT-o3 gpt | 91.30 | 34.10 | 75.00 | 100.00 | 90.00 pass | 65.56 | 40.3 | 32.3 | 100.0 | |
| GPT-6 Astra gpt | 94.50 | 29.10 | 75.00 | 93.80 | 80.00 pass | 65.07 | 33.1 | 30.3 | 100.0 | |
| Gemini 2.5 Pro gemini | 67.00 | 44.80 | 50.00 | 86.30 | 90.00 pass | 57.01 | 93.1 | 37.9 | 90.0 | |
| Gemini 3.1 Pro gemini | 44.50 | 69.30 | 50.00 | 100.00 | 100.00 pass | 55.66 | 81.0 | 19.7 | 100.0 | |
| DeepSeek V4 Pro deepseek | 44.50 | 65.00 | 75.00 | 100.00 | 80.00 pass | 53.73 | 96.0 | 42.5 | 90.0 | |
| GLM-4.6 zhipu | 44.50 | 65.00 | 25.00 | 25.00 | 90.00 pass | 53.73 | 91.6 | 37.4 | 65.0 | |
| 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。