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

CHAMP

Benchmarks

Task NameDataset NameSOTA ResultTrend
Mathematical ReasoningCHAMP standard (test)
Accuracy68.5
36
Mathematical ReasoningCHAMP
Accuracy68.2
32
Retrieval-Augmented GenerationCHAMP
Accuracy45.2
12
Skill retrievalCHAMP
Recall@122.5
11
Skill retrievalCHAMP
nDCG@135.4
11
Showing 5 of 5 rows