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

MC

Benchmarks

Task NameDataset NameSOTA ResultTrend
Multiple Choice Question AnsweringMC (test)
MC Avg78
46
Multiple Choice Question AnsweringMC Benchmarks
MC Avg74.7
22
Chart Question AnsweringMC v1 (test)
Accuracy74.43
11
Word SimilarityMC-30
Spearman Correlation0.67
6
Showing 4 of 4 rows