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

LanEvil

Benchmarks

Task NameDataset NameSOTA ResultTrend
Vision-Language ReasoningLanEvil++
Road Damage (Perturbed) Performance31.58
4
Driving scene understanding robustness evaluationLanEvil ++
Road Damage (Perturbed)31.58
4
Driving scene understanding robustness evaluationLanEvil ++
Road Damage Performance (Perturbed)84.25
4
Showing 3 of 3 rows