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

Mathematical Reasoning on AIME 24 (Pass@1, Token count)

80Pass@1

RED

42.97652.58862.271.812Apr 3, 2026
Updated 12d ago

Evaluation Results

MethodLinks
2026.04
805,793
2026.04
78.98,007
2026.04
78.911,934
2026.04
77.810,677
2026.04
77.85,981
2026.04
77.86,040
2026.04
76.76,173
2026.04
76.76,238
2026.04
75.65,209
2026.04
74.47,894
2026.04
74.43,898
2026.04
73.38,343
2026.04
73.36,771
2026.04
73.38,389
2026.04
73.33,974
2026.04
72.210,931
2026.04
72.28,210
2026.04
72.27,873
2026.04
72.28,109
2026.04
71.17,903
2026.04
71.16,986
2026.04
71.15,492
2026.04
71.14,005
2026.04
7011,125
2026.04
707,873
2026.04
705,802
2026.04
704,906
2026.04
706,829
2026.04
705,002
2026.04
68.95,387
2026.04
68.96,461
2026.04
68.97,766
2026.04
67.85,964
2026.04
67.83,993
2026.04
67.85,115
2026.04
66.75,304
2026.04
57.84,293
2026.04
56.711,673
2026.04
55.68,224
2026.04
55.67,258
2026.04
54.410,438
2026.04
54.45,094
2026.04
53.37,197
2026.04
52.24,341
2026.04
52.25,693
2026.04
47.88,339
2026.04
47.84,507
2026.04
46.78,001
2026.04
45.610,798.9
2026.04
45.68,246
2026.04
45.65,333
2026.04
45.64,809
2026.04
44.46,761
2026.04
44.411,312