Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Mathematical Reasoning on AIME 24 (Avg@32, #Token)
Loading...
45.2
Average Score (Top-32)
GR³
22.632
28.491
34.35
40.209
Mar 11, 2026
Average Score (Top-32)
Token Count
Updated 1mo ago
Evaluation Results
Method
Method
Links
Average Score (Top-32)
Token Count
GR³
Category=Performance-o...
2026.03
45.2
8,381
GRPO
Category=Performance-o...
2026.03
39.6
13,054
DLER-R1-1.5B
Category=Length-orient...
2026.03
34.3
3,839
AdaptThink-1.5B
Category=Length-orient...
2026.03
34.2
9,204
Laser-DE-L4096-1.5B
Category=Length-orient...
2026.03
30.1
5,770
DeepSeek-R1-Distill-1.5B
Category=Initial model
2026.03
30
16,531
LCR1-1.5B
Category=Length-orient...
2026.03
23.5
9,071
Feedback
Search any
task
Search any
task