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

OneReason-Bench

Benchmarks

Task NameDataset NameSOTA ResultTrend
EvolutionOneReason-Bench
Selection Score58.92
13
DerivationOneReason-Bench
I2I Score28.6
7
PerceptionOneReason-Bench
Item Understanding36.91
7
Showing 3 of 3 rows