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

Mathematical Reasoning on AIME 24 (Accuracy, Tokens)

93.3Accuracy

DDC

64.90872.27979.6587.021Jul 20, 2025Sep 8, 2025Oct 29, 2025Dec 19, 2025Feb 8, 2026Mar 31, 2026May 21, 2026
Updated 7d ago

Evaluation Results

MethodLinks
2026.05
93.31.3-
2026.05
92.17.8-
2026.05
89.47.8-
2026.05
86.735.5-
2026.05
86.714.5-
2026.05
86.71.9-
2026.04
86.67--
2026.05
86.611.8-
2026.05
86.48.8-
2026.05
84.910.6-
2026.05
84.820-
2026.04
84.17--
2026.04
84.17--
2026.04
83.33--
2026.04
83.33--
2026.04
83.33--
2026.04
83.33--
2026.05
83.31.2-
2026.05
83.313,426-
2026.05
83.114.1-
2026.05
80.49-
2025.08
80.39--
2026.05
80.224.2-
2025.08
80.19--
2025.08
80.1--
2026.05
80.113.3-
2026.04
80--
2026.04
80--
2026.04
80--
2026.04
80--
2026.04
80--
2026.05
8038.4-
2026.05
8023.2-
2026.05
8012.2-
2026.05
801.3-
2026.05
79.912.8-
2025.08
79.79--
2026.04
79.17--
2025.08
78.58--
2026.04
77.5--
2026.04
77.5--
2026.04
77.5--
2026.05
76.79.6-
2026.05
76.716.8-
2026.05
76.712,854-
2026.04
76.67--
2025.08
76.67--
2025.08
76.45--
2026.04
75.83--
2025.08
75.56--
2026.04
75.52--
2026.04
74.58--
2026.04
74.5--
2025.08
74.48--
2025.08
74.37--
2026.04
74.26--
2026.04
74.23--
2026.05
74.149-
2026.04
74--
2026.04
74--
2026.05
7419.3-
2026.04
73.5--
2026.04
73.33--
2025.07
73.3314,416-
2026.05
73.33.8-
2026.05
73.312,886-
2026.05
73.314,575-
2026.05
73.312,848-
2026.04
73.2--
2025.08
73.12--
2025.08
73.03--
2026.04
73--
2025.08
73--
2026.04
72.6--
2025.07
72.2913,793-
2026.04
72.1--
2026.04
71.8--
2026.04
71.56--
2025.08
71.48--
2025.08
71.25--
2026.04
71.2--
2026.04
71--
2026.04
70.8--
2026.04
70.5--
2026.04
70.42--
2025.07
70.4215,463-
2026.04
70--
2026.04
69.79--
2026.04
69.76--
2026.04
69.7--
2026.04
69.69--
2025.07
68.7514,832-
2026.04
68.33--
2026.04
68.33--
2025.07
68.3313,648-
2025.07
68.3315,131-
2025.07
68.3316,926-
2025.07
68.1313,009-
2026.04
66.67--
2026.04
66--
Showing 100 of 318 rows