Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

AIME

Benchmarks

Task NameDataset NameSOTA ResultTrend
Mathematical ReasoningAIME
AIME Accuracy83.3
283
Mathematical ReasoningAIME 2024
Accuracy93.5
251
Mathematical ReasoningAIME 2025
Accuracy95
227
Mathematical ReasoningAIME 25
Accuracy94.5
201
Mathematical ReasoningAIME24
Accuracy97.3
130
Mathematical ReasoningAIME 24
Accuracy71.1
113
Mathematical ReasoningAIME 2024 (test)
Accuracy96.67
103
Mathematical ReasoningAIME 2025
Pass@180.78
96
Mathematical ReasoningAIME 2024
Pass@183.8
86
Mathematical ReasoningAIME 24
AIME 24 Accuracy93.3
84
Mathematical ReasoningAIME 25
pass@180
65
Mathematical Problem SolvingAIME 2024
Accuracy100
60
Mathematical ReasoningAIME 24
Pass@13,000
59
Mathematical ReasoningAIME 24/25
Accuracy35.3
58
Mathematical ReasoningAIME 2025
Acc77
54
Mathematical Problem SolvingAIME 25
Accuracy93.3
54
Mathematical ReasoningAIME 2024
Pass@173.7
54
Mathematical ReasoningAIME
Token Savings93.7
48
Mathematical ReasoningAIME 2025 (test)
Pass@1 Rate88.9
47
ReasoningAIME 24
Accuracy on AIME 2480
41
ReasoningAIME 25
Accuracy76.9
40
Mathematical ReasoningAIME 24
Pass@168.13
39
Mathematical ReasoningAIME 2025
Accuracy76.92
38
Mathematical ReasoningAIME 2025
Accuracy91.67
37
Math ReasoningAIME 2024
Accuracy0.627
37
Showing 25 of 351 rows
...