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

Long Reasoning on AIME 24 (pass@k, avg@k)

86.67Pass@k

Full

45.0755.8766.6777.47May 19, 2025
Updated 1mo ago

Evaluation Results

MethodLinks
2025.05
86.6766.25
2025.05
83.3356.66
2025.05
83.3352.92
2025.05
83.3358.33
2025.05
83.3357.25
2025.05
83.3364.17
2025.05
8047.08
2025.05
8046.67
2025.05
76.6747.5
2025.05
76.6747.5
2025.05
76.6761.25
2025.05
76.6760
2025.05
73.3344.17
2025.05
73.3342.92
2025.05
73.3347.92
2025.05
73.3343.75
2025.05
73.3348.75
2025.05
7045.83
2025.05
66.6736.25
2025.05
65.3335.42
2025.05
63.3336.5
2025.05
63.3343.34
2025.05
46.6730
2025.05
46.6732.5