Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Mathematics

Benchmarks

Task NameDataset NameSOTA ResultTrend
Mathematical ReasoningMathematics out-of-domain (test)
Accuracy75.9
26
Mathematical ReasoningMathematics
Accuracy85.9
24
Mathematical ReasoningMATHEMATICS
Accuracy74.1
22
Mathematical ReasoningMathematics
Pass@165.8
18
Category RetrievalMathematics Amazon (test)
R@5031.4
15
Link PredictionMathematics
PREC@171.22
14
RerankingMathematics
NDCG@547.1
14
Showing 7 of 7 rows