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

Geometry Problem Solving on GeoQA (test)

92.3Choice Accuracy

Human

38.927252.783666.6480.4964May 29, 2025Jul 12, 2025Aug 26, 2025Oct 10, 2025Nov 24, 2025Jan 8, 2026Feb 22, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2025.05
92.3
2025.05
86.2
85.6
65.2
2025.05
64.1
2026.02
60.74
60
2025.05
57.4
2026.02
52.52
2026.02
52.52
2026.02
51.19
2026.02
46.42
2026.02
40.98