Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Math Reasoning on AIME (test)
Loading...
3,098
Token Usage (Optimization Phase, Thousands)
ETGPO
2,525.92
6,387.46
10,249
14,110.54
Feb 1, 2026
Token Usage (Optimization Phase, Thousands)
Updated 1mo ago
Evaluation Results
Method
Method
Links
Token Usage (Optimization Phase, Thousands)
ETGPO
Backbone=DeepSeek-V3.1...
2026.02
3,098
GEPA
Backbone=DeepSeek-V3.1...
2026.02
9,899
MIPROv2
Backbone=DeepSeek-V3.1...
2026.02
17,400
Feedback
Search any
task
Search any
task