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

Geometric Problem Solving on GeoTrust (test)

45.83Accuracy

OpenAI-o3

-0.096411.826823.7535.6732Apr 22, 2025
Updated 23d ago

Evaluation Results

MethodLinks
2025.04
45.83110
2025.04
45.83-
2025.04
43.33104
2025.04
43.33104
2025.04
43.33-
2025.04
43.33-
2025.04
37.0889
2025.04
28.3368
2025.04
28.33-
2025.04
27.566
2025.04
27.5-
2025.04
25.8362
2025.04
25.83-
2025.04
4.5811
2025.04
1.674