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

MMhops

Benchmarks

Task NameDataset NameSOTA ResultTrend
Multi-hop Question AnsweringMMhops Comparison (test)
Accuracy29.39
13
Multi-hop Question AnsweringMMhops Bridging (test)
String Success Rate58.8
13
Visual Question AnsweringMMhops Comparison
Accuracy39.8
7
Visual Question AnsweringMMhops Bridging
Accuracy67.2
7
Showing 4 of 4 rows