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

Math Reasoning on AMC23 (Pass@1, #Tokens)

100Pass@1 Accuracy

ReBalance

37.653.87086.2Apr 15, 2025Jun 13, 2025Aug 11, 2025Oct 10, 2025Dec 8, 2025Feb 5, 2026Apr 6, 2026
Updated 10d ago

Evaluation Results

MethodLinks
2026.03
1005,230
2026.03
957,240
2026.03
955,360
2026.03
955,527
2026.03
955,050
2026.03
956,582
2026.03
956,435
2026.03
956,341
2026.03
956,064
2026.03
92.54,667
2026.03
92.56,217
2026.03
92.54,717
2026.03
92.56,702
2026.03
906,126
2026.03
907,119
2026.03
906,544
2026.03
906,055
2026.03
87.54,440
2026.03
87.54,503
2026.03
87.57,021
2026.03
856,375
2026.03
853,654
2026.03
853,795
2026.03
855,121
2026.04
82.511,269
2026.04
80.56,916
2026.03
805,157
2026.04
808,212
2026.04
79.85,846
2026.04
79.56,945
2026.03
77.55,164
2026.04
77.55,587
2026.04
77.56,018
2026.03
755,084
2026.04
733,731
2026.03
72.56,505
2026.03
72.56,236
2026.03
72.55,744
2026.04
72.56,110
2026.04
72.53,392
2026.04
72.53,485
2026.04
714,660
2025.04
70-
2026.04
705,923
2026.04
705,882
2026.04
704,675
2025.04
67.5-
2026.04
67.56,054
2026.03
651,911
2025.04
65-
2026.03
62.58,239
2026.03
62.56,812
2025.04
62.5-
2025.04
62.5-
2025.04
62.5-
2026.04
62.54,053
2026.04
62.52,561
2026.04
612,603
2026.04
60.52,436
2026.03
603,267
2026.03
603,302
2025.04
60-
2025.04
60-
2026.04
602,708
2026.03
57.55,132
2026.04
57.52,209
2025.04
55-
2025.04
40-