OpenCompass
Benchmarks
Task NameDataset NameSOTA ResultTrendResults
OpenCompass SIQA, GSM8K, WiC, HumanEval, MMLU, CSQA
66.79SIQA
30
OpenCompass
65.1OpenCompass Score
19
OpenCompass
79.9Average Score
15
OpenCompass MATH, GSM8K, HumanEval, MMLU, CEVAL, CMMLU, BoolQ, CSQA (test)
4Average K
12
Opencompass Image Benchmark (val)
84MMBench Accuracy
12
OpenCompass (test)
69.58CMMLU
11
OpenCompass
84.88cMMLU
11
Opencompass
69.1Average Score
10
OpenCompass 95% masking September 30, 2024 cutoff (temporal split)
8.75RMSE
10
OpenCompass
82.2MMBench
6