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

MSVAMP

Benchmarks

Task NameDataset NameSOTA ResultTrend
Math ReasoningMSVAMP (test)
Average Accuracy83.9
45
Multilingual Mathematical ReasoningMSVAMP
Accuracy (English)75
33
Mathematical ReasoningMSVAMP
Average Accuracy80.21
28
Mathematical ReasoningMSVAMP Bangla
Accuracy (Original)81.1
13
Multilingual Mathematical ReasoningMSVAMP (all)
Accuracy89
12
Multilingual Mathematical ReasoningMSVAMP out-of-domain
Accuracy89.4
12
Multilingual Mathematical ReasoningMSVAMP in-domain
Accuracy88.4
12
Mathematical ReasoningBn-MSVAMP (test)
Accuracy82.3
12
Showing 8 of 8 rows