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

Molmo QA Benchmarks

Benchmarks

Task NameDataset NameSOTA ResultTrend
Video Question AnsweringMolmo QA Benchmarks Long Video 19
Long Video Average80.4
22
Multi-Image Question AnsweringMolmo QA Benchmarks Multi-Image 19
Average Score (Multi-Image)81.9
20
Image Question AnsweringMolmo QA Benchmarks Image 19
Image Average Accuracy86.2
20
Showing 3 of 3 rows