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

Mathematical Reasoning on AIME '24 (Accuracy, Avg, Speedup)

93.3Accuracy

all-attention

-1.23623.30747.8572.393Mar 25, 2026Mar 29, 2026Apr 3, 2026Apr 7, 2026Apr 12, 2026Apr 16, 2026Apr 21, 2026
Updated 29d ago

Evaluation Results

MethodLinks
2026.04
93.3--
2026.04
93.3--
2026.04
90--
2026.04
90--
2026.04
90--
2026.04
86.7--
2026.04
86.7--
2026.04
83.3--
2026.04
83.3--
2026.04
80--
2026.04
76.7--
2026.04
76.7--
2026.04
66.7--
2026.04
66.7--
2026.03
66.6759.531.62
2026.04
63.3--
2026.04
60--
2026.03
56.6756.66-
2026.03
4053.541.63
2026.03
36.6751.01-
2026.04
26--
2026.04
25.7--
2026.04
25.3--
2026.04
24.5--
2026.04
23.8--
2026.03
23.3337.091.61
2026.04
22.5--
2026.04
21.9--
2026.04
21.5--
2026.04
21--
2026.03
2034.79-
2026.04
18.8--
2026.03
16.6717.491.67
2026.03
13.3314.63-
2026.04
5--
2026.04
4.6--
2026.04
3.8--
2026.04
3.3--
2026.04
2.4--
2026.06
-76-
2026.06
-79.3-
2026.06
-79.5-
2026.06
-80.83-