Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

MMLU & GPQA

Benchmarks

Task NameDataset NameSOTA ResultTrend
General ReasoningMMLU & GPQA
Average Score62.62
13
Out-of-Distribution GeneralizationMMLU-Redux and GPQA-Diamond (out-of-distribution)
Average Accuracy76.7
4
Showing 2 of 2 rows