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

MMR-Bench

Benchmarks

Task NameDataset NameSOTA ResultTrend
LLM RoutingMMR-Bench
nAUC0.918
37
Deep Research Report GenerationMMR Bench+
Informativeness4.15
9
LLM RoutingMMR-Bench Out-of-domain
nAUC0.6701
9
Showing 3 of 3 rows