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

MCR-Bench

Benchmarks

Task NameDataset NameSOTA ResultTrend
Reproducibility EvaluationMCR-Bench
MSE0
40
Conflict ResolutionMCR-BENCH
Accuracy (Neutral)45.9
6
Showing 2 of 2 rows