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

Abstract Reasoning on MMStar

63.21Accuracy

Nash

53.839656.272358.70561.1377May 19, 2026
Updated 14d ago

Evaluation Results

MethodLinks
2026.05
63.21
2026.05
61.07
2026.05
57.25
2026.05
57.2
2026.05
54.2