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

BEAF

Benchmarks

Task NameDataset NameSOTA ResultTrend
Vision-Language ReasoningBEAF (test)
Simple Accuracy88.4
7
Paired-prompt evaluationBEAF (sample)
Simple Accuracy90.67
2
Showing 2 of 2 rows