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

Math Reasoning on AIME 24 (Pass@1, #Tokens)

73.3Pass@1 Score

Dynasor-CoT

4.03622.0184057.982Mar 12, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.03
73.310,369
2026.03
73.39,464
2026.03
708,898
2026.03
708,885
2026.03
7010,350
2026.03
66.710,888
2026.03
66.710,212
2026.03
66.79,973
2026.03
66.714,342
2026.03
66.710,507
2026.03
66.78,190
2026.03
63.310,322
2026.03
63.311,438
2026.03
63.311,156
2026.03
63.310,344
2026.03
6010,507
2026.03
6010,034
2026.03
56.78,345
2026.03
53.38,457
2026.03
53.39,948
2026.03
508,924
2026.03
506,844
2026.03
46.711,923
2026.03
46.711,663
2026.03
46.79,864
2026.03
43.310,112
2026.03
33.311,894
2026.03
33.310,668
2026.03
308,225
2026.03
3010,134
2026.03
26.710,564
2026.03
26.74,427
2026.03
23.312,451
2026.03
23.310,785
2026.03
208,135
2026.03
6.76,998