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

PPE Correctness

Benchmarks

Task NameDataset NameSOTA ResultTrend
Reward ModelingPPE Correctness (test)
PPE Corr75
26
Correctness EvaluationPPE Correctness (test)
Kuiper0.0643
8
Showing 2 of 2 rows