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

MATH, GPQA, MMLU, GSM8K, ARC

Benchmarks

Task NameDataset NameSOTA ResultTrend
General ReasoningMATH-500, GPQA-D, MMLU-P, GSM8K, ARC-C Aggregate
Average Score85.41
18
Showing 1 of 1 rows