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

Mathematical Reasoning on AIME 2023 (Accuracy and Token Count)

73.33Accuracy (%)

RAG

-2.933216.865936.66556.4641Sep 26, 2025Nov 2, 2025Dec 10, 2025Jan 17, 2026Feb 24, 2026Apr 3, 2026May 11, 2026
Updated 2mo ago

Evaluation Results

MethodLinks
2025.09
73.3311,750.4
2025.09
7044,736.6
2025.09
63.3311,366.2
2025.09
63.3349,529.87
2025.09
63.3346,998.97
2025.09
63.3310,623.03
2025.09
6012,728.53
2025.09
6012,096.93
2025.09
56.6712,430.8
2025.09
53.3311,829.9
2025.09
53.3313,341.63
2025.09
5012,812.63
2025.09
5056,428.9
2025.09
5010,698.93
2025.09
46.6713,277.83
2025.09
46.6710,003.3
2025.09
36.449,331.67
2025.09
33.3311,676.13
2025.09
33.3311,456.13
2025.09
33.3345,657.83
2025.09
33.3312,577.16
2026.05
33.3-
2025.09
23.3345,898.9
2026.05
16.7-
2026.05
16.7-
2025.09
16.6742,095.83
2025.09
16.678,292.7
2025.09
13.3310,421.53
2026.05
13.3-
2026.05
13.3-
2025.09
1330,258.34
2025.09
1010,849.5
2025.09
1010,933.53
2026.05
10-
2026.05
6.7-
2025.09
03,058.8