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

Physics on TheoremQA

58.8Accuracy

TroVE

29.47237.08644.752.314May 27, 2025
Updated 1mo ago

Evaluation Results

MethodLinks
2025.05
58.8-
2025.05
58.8-
2025.05
57.9-
2025.05
57.9-
2025.05
57.9-
2025.05
57-
2025.05
57-
2025.05
57-
2025.05
53.5-
2025.05
50.9-
2025.05
49.1-
2025.05
48.2-
2025.05
48.2-
2025.05
48.2-
2025.05
45.6-
2025.05
44.7-
2025.05
44.7-
2025.05
42.1-
2025.05
40.4-
2025.05
40.4-
2025.05
39.8-
2025.05
38.9-
2025.05
35.1-
2025.05
35.1-
2025.05
33.3-
2025.05
33.3-
2025.05
33.3-
2025.05
30.6-
2025.05
-35.7
2025.05
-43.2
2025.05
-43.9
-43.6
2025.05
-52.2
2025.05
-51.1
-54.8