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

Mathematics on AIME24

77.3Accuracy

DSMoE

-2.228818.418139.06559.7119Jan 27, 2026Feb 7, 2026Feb 19, 2026Mar 3, 2026Mar 14, 2026Mar 26, 2026Apr 7, 2026
Updated 11d ago

Evaluation Results

MethodLinks
2026.04
77.3--
2026.02
76.7-13.4
2026.02
70-6.7
2026.04
70--
2026.02
66.7-23.4
2026.02
66.7-3.4
2026.02
66.7-3.4
2026.03
66.67--
2026.03
66.67--
2026.02
63.3-20
2026.02
63.3--
2026.02
63.3-0
2026.02
63.3-0
2026.04
63.3--
2026.04
63.3--
2026.01
60.87--
2026.02
56.7-13.4
2026.02
56.7-13.4
2026.02
56.7-13.4
2026.04
56.7--
2026.04
56.7--
2026.04
56.7--
2026.04
50--
2026.01
47.83--
2026.02
46.7-3.4
2026.01
43.48--
2026.02
43.3--
2026.01
39.13--
2026.01
34.78--
2026.03
33.33--
2026.04
26.67--
2026.01
26.08--
2026.03
23.33--
2026.04
16.67--
2026.04
13.33--
2026.04
13.33--
2026.04
2.08--
2026.04
0.83--
2026.02
-73.33-
2026.02
-71.67-
2026.02
-80.83-
2026.02
-81.46-
2026.02
-86.67-
2026.02
-83.75-