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

REAL-Colon-Reason

Benchmarks

Task NameDataset NameSOTA ResultTrend
Surgical Video Question AnsweringREAL-Colon-Reason (Overall)
EM58.4
11
Surgical Video Question AnsweringREAL-Colon-Reason Level 3
Exact Match (EM)51.5
11
Surgical Video Question AnsweringREAL-Colon-Reason (Level 1)
EM65.3
11
Showing 3 of 3 rows