Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Math & Logic on MATH (Performance %)
Loading...
4.56
Performance (%)
SPIN
2.792
3.251
3.71
4.169
Jan 13, 2026
Performance (%)
Updated 4d ago
Evaluation Results
Method
Method
Links
Performance (%)
SPIN
Iteration=Iter4
2026.01
4.56
T-SPIN
Iteration=Iter4
2026.01
3.94
T-SPIN
Iteration=Iter3
2026.01
3.85
SPIN
Iteration=Iter3
2026.01
3.71
T-SPIN
Iteration=Iter0
2026.01
3.53
SPIN
Iteration=Iter2
2026.01
3.5
SPIN
Iteration=Iter1
2026.01
3.43
T-SPIN
Iteration=Iter2
2026.01
3.43
T-SPIN
Iteration=Iter1
2026.01
3.32
Mistral-7B
Configuration=Base
2026.01
3.27
SFT
Method=Supervised Fine...
2026.01
3.08
SPIN
Iteration=Iter0
2026.01
2.86
Feedback
Search any
task
Search any
task
