Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Open Question Answering on MATH500 (test)
Loading...
0.94
Accuracy
GRPO
0.8464
0.8707
0.895
0.9193
Feb 10, 2026
Accuracy
Answer Length
Updated 4d ago
Evaluation Results
Method
Method
Links
Accuracy
Answer Length
GRPO
2026.02
0.94
3,962
FlashThink
2026.02
0.938
3,050
AdaptThink
2026.02
0.938
2,130
ESTAR
optimization=RL
2026.02
0.938
635
ESTAR-FT
mode=fine-tuned
2026.02
0.934
2,401
ESTAR-LITE
early_stopping=classif...
2026.02
0.932
2,019
Length-Penalty
explicit_length_penalt...
2026.02
0.924
3,190
O1-Pruner
2026.02
0.916
2,856
No-Thinking
reasoning=disabled
2026.02
0.85
1,139
Feedback
Search any
task
Search any
task