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

VSP

Benchmarks

Task NameDataset NameSOTA ResultTrend
Multimodal ReasoningVSP IID
Accuracy82.8
14
Visual ReasoningVSP
Accuracy78.36
14
Visual UnderstandingVSP
Accuracy75.83
11
Visual ReasoningVSP-Super
Accuracy (Scale 16)100
10
Visual ReasoningVSP
Accuracy (Scale 3)100
10
Visual Spatial PlanningVSP (test)
Average Accuracy99
9
Showing 6 of 6 rows