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

Mathematical Reasoning on AMC23 (Pass@k)

98.6Pass@k

Qwen2.5-7B + PPO

44.31258.40672.586.594Sep 28, 2025
Updated 5d ago

Evaluation Results

MethodLinks
2025.09
98.6
2025.09
98.4
2025.09
98.3
2025.09
98
2025.09
97.8
2025.09
97
2025.09
96.8
2025.09
96.7
2025.09
96.5
2025.09
95.9
2025.09
95.7
2025.09
95.4
2025.09
95.1
2025.09
94.9
2025.09
94.7
2025.09
94.6
2025.09
94.5
2025.09
93.8
2025.09
93.5
2025.09
92.4
2025.09
92.2
2025.09
91.9
2025.09
91.7
2025.09
88.5
2025.09
87.3
2025.09
73.5
2025.09
64.5
2025.09
63.2
2025.09
46.5
2025.09
46.4