Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Tool-Integrated Reasoning on AIME 25 (test accuracy)
Loading...
31.25
Test Accuracy
Token-ALP
23.7724
25.7137
27.655
29.5963
Mar 19, 2026
Test Accuracy
Updated 26d ago
Evaluation Results
Method
Method
Links
Test Accuracy
Token-ALP
temperature=1.0, sampl...
2026.03
31.25
Token-MIS
temperature=1.0, sampl...
2026.03
28.85
Seq-ALP
temperature=1.0, sampl...
2026.03
28.65
GRPO
temperature=1.0, sampl...
2026.03
24.79
Seq-MIS
temperature=1.0, sampl...
2026.03
24.17
Seq-Bypass
temperature=1.0, sampl...
2026.03
24.06
Feedback
Search any
task
Search any
task
