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

Multi-modal Reasoning on Geometry3K

37.9Pass@1

APMPO

25.21228.50631.835.094Apr 11, 2026
Updated 2mo ago

Evaluation Results

MethodLinks
2026.04
37.9
2026.04
37.2
2026.04
36.5
2026.04
36.1
2026.04
35.6
2026.04
35.6
2026.04
35.3
2026.04
34.8
2026.04
34.4
2026.04
25.7
2026.04
25.7