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

Multimodal Reasoning on VisualPuzzles (OOD)

33.9Overall Accuracy

AMVL

27.493629.156830.8232.4832Jul 1, 2026
Updated 23d ago

Evaluation Results

MethodLinks
2026.07
33.932.4427.9652.528.2330.77
2026.07
32.9637.7927.014126.7927.01
2026.07
32.7137.0221.847.526.3221.8
2026.07
31.332.423.738.528.732.5
2026.07
30.834.726.53727.328.7
2026.07
27.7428.6323.223628.2324.12