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

Visual Probe

Benchmarks

Task NameDataset NameSOTA ResultTrend
PerceptionVisual Probe
Pass@467.9
16
PerceptionVisual Probe
Pass@145.8
16
General EvaluationVisual Probe-H
Score38.7
7
Showing 3 of 3 rows