历史专项测试
历史数据存档。查看近期模型，请返回模型能力评测。
知识与推理 · MMLU-Pro
记录保留原模型配置与数据提供方；计算机知识分项衡量知识，不是代码项目完成率。
262 条 · 按总正确率降序缺测记为 —
| 模型／配置 | 总正确率 | 数据提供方 |
|---|---|---|
| 40.7% | TIGER-Lab | |
| 39.8% | TIGER-Lab | |
| 39.2% | TIGER-Lab | |
| 39.1% | TIGER-Lab | |
| 38.2% | TIGER-Lab | |
| 38.0% | TIGER-Lab | |
| 37.9% | TIGER-Lab | |
| 37.9% | TIGER-Lab | |
| 37.9% | TIGER-Lab | |
| 37.5% | TIGER-Lab | |
| 37.2% | TIGER-Lab | |
| 37.1% | TIGER-Lab | |
| 37.0% | Self-Reported | |
| 37.0% | Self-Reported | |
| 36.9% | TIGER-Lab | |
| 36.6% | TIGER-Lab | |
| 35.4% | TIGER-Lab | |
| 35.3% | TIGER-Lab | |
| 34.4% | TIGER-Lab | |
| 33.7% | TIGER-Lab |
'%20fill-rule='nonzero'%3e%3c/path%3e%3cdefs%3e%3clinearGradient%20id='lobe-icons-qwen-_R_0_'%20x1='0%25'%20x2='100%25'%20y1='0%25'%20y2='0%25'%3e%3cstop%20offset='0%25'%20stop-color='%236336E7'%20stop-opacity='.84'%3e%3c/stop%3e%3cstop%20offset='100%25'%20stop-color='%236F69F7'%20stop-opacity='.84'%3e%3c/stop%3e%3c/linearGradient%3e%3c/defs%3e%3c/svg%3e){kind=small}
'%3e%3c/path%3e%3cpath%20d='M4.148%209.181c1.759.41%203.544.66%205.343.789%201.572.113%203.15.11%204.727.036%201.571-.073%203.118-.286%204.658-.569.536-.098%201.055-.262%201.613-.247%201.145.029%201.934.635%202.208%201.715.395%201.551.415%203.105-.007%204.646a9.535%209.535%200%2001-2.305%204.101%2011.066%2011.066%200%2001-4.22%202.786c-1.715.64-3.493.846-5.32.68a8.637%208.637%200%2001-1.4-.224.36.36%200%2000-.292.053C7.93%2023.669%206.6%2024.01%205.176%2024a7.643%207.643%200%2001-1.198-.114c-.77-.126-1.044-.823-.568-1.43.26-.33.496-.67.642-1.064.067-.18.13-.361.184-.546a.698.698%200%2000-.197-.75c-.886-.861-1.628-1.83-2.143-2.946-1.078-2.334-1.19-4.717-.302-7.136a9.826%209.826%200%2001.584-1.275l.072.011c.921.207%201.554.351%201.898.431z'%20fill='url(%23lobe-icons-open-chat-1-_R_0_)'%3e%3c/path%3e%3cdefs%3e%3clinearGradient%20id='lobe-icons-open-chat-0-_R_0_'%20x1='34.383%25'%20x2='57.623%25'%20y1='37.415%25'%20y2='59.204%25'%3e%3cstop%20offset='0%25'%20stop-color='%236595F1'%3e%3c/stop%3e%3cstop%20offset='100%25'%20stop-color='%23336BD7'%3e%3c/stop%3e%3c/linearGradient%3e%3clinearGradient%20id='lobe-icons-open-chat-1-_R_0_'%20x1='50%25'%20x2='50%25'%20y1='0%25'%20y2='100%25'%3e%3cstop%20offset='0%25'%20stop-color='%236595F1'%3e%3c/stop%3e%3cstop%20offset='100%25'%20stop-color='%23336BD7'%3e%3c/stop%3e%3c/linearGradient%3e%3c/defs%3e%3c/svg%3e){kind=small}
LLaDA
关闭详情数据提供方：Self-Reported · 参数规模：8 B
- 总正确率
- 37.0%
- 数学
- —
- 计算机知识
- —
- 物理
- —
- 化学
- —
- 生物
- —
- 工程
- —
- 经济
- —
- 商业
- —
- 健康
- —
- 心理
- —
- 法律
- —
- 历史
- —
- 哲学
- —
- 其他
- —
来源、版本与使用范围
数据版本：4623b7c68d2276218d487464b0608dc978f4b301
来源许可证：Apache-2.0。模型自身许可证与成绩文件许可证分别核对。本页未运行模型评测；不同来源或配置记录不合并，价格未提供。
固定版本数据文件