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

ORZ

Benchmarks

Task NameDataset NameSOTA ResultTrend
Mathematical Problem SolvingORZ-57K AIME24/25, Minerva, Math500, AMC, OlympiadBench (test)
Accuracy (Minerva)31.66
3
Showing 1 of 1 rows