Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Math Reasoning on AIME25 (Accuracy)
Loading...
94.6
AIME25 Accuracy
GPT-5
-0.352
24.299
48.95
73.601
Jan 7, 2026
AIME25 Accuracy
Updated 4d ago
Evaluation Results
Method
Method
Links
AIME25 Accuracy
GPT-5
Evaluation Protocol=Cl...
2026.01
94.6
Gemini2.5-Pro
Evaluation Protocol=Cl...
2026.01
86.7
ATLAS (cluster)
Evaluation Protocol=In...
2026.01
40
GPT-4.1
Evaluation Protocol=Cl...
2026.01
33.3
ATLAS (RL)
Evaluation Protocol=Ou...
2026.01
33.3
RouterDC
Evaluation Protocol=In...
2026.01
23.3
FS Router
Evaluation Protocol=Tr...
2026.01
13.3
BertRouter
Evaluation Protocol=In...
2026.01
13.3
MLPRouter
Evaluation Protocol=In...
2026.01
10
GPT-4o
Evaluation Protocol=Cl...
2026.01
6.7
ZS Router
Evaluation Protocol=Tr...
2026.01
6.7
BertRouter
Evaluation Protocol=Ou...
2026.01
6.7
Random Router
Evaluation Protocol=Tr...
2026.01
3.3
RouterDC
Evaluation Protocol=Ou...
2026.01
3.3
MLPRouter
Evaluation Protocol=Ou...
2026.01
3.3
ATLAS (cluster)
Evaluation Protocol=Ou...
2026.01
3.3
Feedback
Search any
task
Search any
task