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

Specialized Knowledge Tasks (ARC-C, SciQ, PubMedQA, MathQA, MMLU)

Benchmarks

Task NameDataset NameSOTA ResultTrend
Question AnsweringSpecialized Knowledge Tasks (ARC-C, SciQ, PubMedQA, MathQA, MMLU) zero-shot
ARC-C29.9
8
Showing 1 of 1 rows