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

AR-Bench

Benchmarks

Task NameDataset NameSOTA ResultTrend
Active ReasoningAR-Bench-DC
Exact Accuracy61
23
Active ReasoningAR-Bench-SP
Non-strict Semantic Equivalence54
10
Showing 2 of 2 rows