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

AIME

Benchmarks

Task NameDataset NameSOTA ResultTrend
Mathematical ReasoningAIME 2024
Accuracy93.3
525
Mathematical ReasoningAIME 2024
Accuracy79.3
394
Mathematical ReasoningAIME 2025
Accuracy99.2
378
Mathematical ReasoningAIME 2024
Accuracy94
370
Mathematical ReasoningAIME 24
Accuracy93.3
358
Mathematical ReasoningAIME 2025
Accuracy96.7
353
Mathematical ReasoningAIME 2024 (test)
Accuracy96.67
294
Mathematical ReasoningAIME
AIME Accuracy83.3
288
Mathematical ReasoningAIME 2024
Pass@1 Accuracy83.33
243
Mathematical ReasoningAIME 2025
Accuracy95
227
Mathematical ReasoningAIME 25
Accuracy94.5
201
Mathematical ReasoningAIME 2025
Pass@1 Accuracy98.6
192
Mathematical ReasoningAIME 2025 (test)
Pass@1 Rate89.1
191
Mathematical ReasoningAIME 25
Pass@1 Accuracy89.1
190
Mathematical ReasoningAIME 24/25
Accuracy80
171
Mathematical ReasoningAIME24
Accuracy97.3
160
Mathematical ReasoningAIME 24
Pass@1 Accuracy82.7
153
Mathematical ReasoningAIME25
Accuracy (ACC)75
119
Mathematical ReasoningAIME 24
Pass@1 Accuracy76.25
117
Mathematical ReasoningAIME24
Pass@1 Accuracy78.9
117
Mathematical Problem SolvingAIME 2024
Accuracy100
113
Mathematical ReasoningAIME 24
Accuracy71.1
113
Mathematical ReasoningAIME 25
Accuracy86.7
112
MathematicsAIME25
Accuracy93.33
103
Mathematical ReasoningAIME 2025
Pass@180.78
96
Showing 25 of 1209 rows
...