Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Mathematical Reasoning on MultiArith (val)
Loading...
1,640
Tokens at Best Step (K)
GrIPS
148.64
535.82
923
1,310.18
Apr 8, 2026
Tokens at Best Step (K)
Best Step
Updated 1mo ago
Evaluation Results
Method
Method
Links
Tokens at Best Step (K)
Best Step
GrIPS
2026.04
1,640
10
ProTeGi
2026.04
1,455
7
CriSPO
2026.04
1,050
5
APE
2026.04
824
6
ZERA
2026.04
460
3
OPRO
2026.04
377
2
aPSF
2026.04
206
1
Feedback
Search any
task
Search any
task
