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

Math Reasoning on Olympiad (Accuracy, Pass@1)

68.55Accuracy

VCORE

15.7729.472543.17556.8775Oct 31, 2025
Updated 3mo ago

Evaluation Results

MethodLinks
2025.10
68.5568.55
2025.10
67.6667.66
2025.10
66.1766.17
2025.10
65.1365.13
2025.10
64.9964.99
2025.10
64.8464.84
2025.10
63.863.8
2025.10
63.863.8
2025.10
63.6563.65
2025.10
62.9162.91
2025.10
62.3162.31
2025.10
62.3162.31
2025.10
61.7261.72
2025.10
61.7261.72
2025.10
61.5761.57
2025.10
60.9860.98
2025.10
60.0960.09
2025.10
60.0960.09
2025.10
25.9625.96
2025.10
23.5923.59
2025.10
22.5522.55
2025.10
22.5522.55
2025.10
18.8418.84
2025.10
17.817.8