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

RefMem-Bench

Benchmarks

Task NameDataset NameSOTA ResultTrend
Single-Choice Question AnsweringRefMem-Bench
Accuracy66.2
14
Multi-Choice Question AnsweringRefMem-Bench
Accuracy59.4
14
Showing 2 of 2 rows