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

Mathematical Reasoning on AIME-24 (Avg. Pass@1)

73.75Avg. Pass@1

Baseline (Dense)

-2.9516.962536.87556.7875Dec 18, 2025
Updated 1mo ago

Evaluation Results

MethodLinks
2025.12
73.7514,400
2025.12
70.4215,900
2025.12
65.8317,900
2025.12
60.8317,900
2025.12
50.4211,300
2025.12
47.9214,600
2025.12
41.2514,000
2025.12
39.5812,500
2025.12
36.2514,800
2025.12
25.3328,800
2025.12
7.522,900
2025.12
07,500
2025.12
06,900