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

SFE

Benchmarks

Task NameDataset NameSOTA ResultTrend
Scientific Multimodal ReasoningSFE
Accuracy44.06
10
Scientific ReasoningSFE ZH Chinese
Score35.69
9
Scientific ReasoningSFE English
Score36.49
9
STEMSFE
Pass@161.9
7
Scientific ReasoningSFE
Accuracy44.06
7
Scientific Multimodal TasksSFE
Score58.9
5
Showing 6 of 6 rows