Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Science Reasoning on Science (out-of-distribution)
Loading...
65.12
Accuracy
CalibRL
53.8984
56.8117
59.725
62.6383
Feb 22, 2026
Accuracy
Updated 3d ago
Evaluation Results
Method
Method
Links
Accuracy
CalibRL
2026.02
65.12
LUFFY
2026.02
63.11
GRPO
2026.02
61.99
DAPO
2026.02
61.61
RL-PLUS
2026.02
61.21
SFT+GRPO
2026.02
54.33
Feedback
Search any
task
Search any
task