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

Physics problem solving on Scibench fund

74.6Accuracy

PoT + REFTOOL

35.0845.3455.665.86May 27, 2025
Updated 1mo ago

Evaluation Results

MethodLinks
2025.05
74.6-
2025.05
73.2-
2025.05
73.2-
2025.05
73.2-
2025.05
73.2-
2025.05
73.2-
2025.05
71.8-
2025.05
70.4-
2025.05
69-
2025.05
64.8-
2025.05
63.4-
2025.05
63.4-
2025.05
62-
2025.05
59.2-
2025.05
59.2-
2025.05
59.2-
2025.05
57.7-
2025.05
57.7-
2025.05
56.3-
2025.05
56.3-
2025.05
54.9-
2025.05
53.5-
2025.05
53.5-
2025.05
36.6-
-53.9
2025.05
-59.5
2025.05
-63.7
2025.05
-65.1
-67.6
2025.05
-67.6