Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Closed Question Answering on JAMA (test)
Loading...
57.8
Accuracy
GRPO
47.816
50.408
53
55.592
Feb 10, 2026
Accuracy
Result Length
Updated 4d ago
Evaluation Results
Method
Method
Links
Accuracy
Result Length
GRPO
2026.02
57.8
2,634
ESTAR-FT
mode=fine-tuned
2026.02
57.2
689
ESTAR-LITE
early_stopping=classif...
2026.02
56.6
419
ESTAR
optimization=RL
2026.02
56.1
352
FlashThink
2026.02
55.8
2,161
AdaptThink
2026.02
55.8
1,102
Length-Penalty
explicit_length_penalt...
2026.02
55.4
1,872
O1-Pruner
2026.02
53.2
1,981
No-Thinking
reasoning=disabled
2026.02
48.2
369
Feedback
Search any
task
Search any
task