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
479
Mathematical ReasoningAIME 2024
Accuracy94
370
Mathematical ReasoningAIME 24
Accuracy93.3
318
Mathematical ReasoningAIME 2025
Accuracy96.7
311
Mathematical ReasoningAIME
AIME Accuracy83.3
288
Mathematical ReasoningAIME 2024
Pass@1 Accuracy83.33
236
Mathematical ReasoningAIME 2025
Accuracy95
227
Mathematical ReasoningAIME 2024
Accuracy77.78
220
Mathematical ReasoningAIME 2025
Accuracy99.2
214
Mathematical ReasoningAIME 2024 (test)
Accuracy96.67
209
Mathematical ReasoningAIME 25
Accuracy94.5
201
Mathematical ReasoningAIME 2025
Pass@1 Accuracy98.6
192
Mathematical ReasoningAIME 25
Pass@1 Accuracy89.1
178
Mathematical ReasoningAIME 24/25
Accuracy80
171
Mathematical ReasoningAIME24
Accuracy97.3
160
Mathematical ReasoningAIME 2025 (test)
Pass@1 Rate88.9
148
Mathematical ReasoningAIME 24
Pass@1 Accuracy82.7
128
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
Mathematical ReasoningAIME 24
Pass@1 Accuracy76.25
103
MathematicsAIME25
Accuracy93.33
103
Mathematical ReasoningAIME 2025
Pass@180.78
96
Mathematical ReasoningAIME 2024
Pass@183.8
86
Showing 25 of 980 rows
...