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

ARBench

Benchmarks

Task NameDataset NameSOTA ResultTrend
Active ReasoningARBench
DC Score46.7
16
Active ReasoningARBench-GN
Accuracy45.3
13
Active ReasoningARBench SP
Accuracy43.1
13
Showing 3 of 3 rows