Cmmlu
评估指标
cmmlu
cmmluchinaspecific
cmmluhumanities
cmmluother
cmmlusocialscience
cmmlustem
key
model
num
org
rank
time
评测结果
各个模型在此基准测试上的表现结果
模型名称 | cmmlu | cmmluchinaspecific | cmmluhumanities | cmmluother | cmmlusocialscience | cmmlustem | key | model | num | org | rank | time | Paper Title | Repository |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Base | 83.600000 | 83.700000 | 87.500000 | 86.100000 | 84.300000 | 77.500000 | 1.000000 | Qwen-72B | 72B | Alibaba | 1.000000 | 2023/11/30 | - | - |
0 of 1 row(s) selected.