Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Reward Prediction on PIQA (out-of-domain)
Loading...
82.22
Accuracy
R1-p
71.82
74.52
77.22
79.92
Mar 13, 2026
Accuracy
Updated 26d ago
Evaluation Results
Method
Method
Links
Accuracy
R1-p
Backbone=Qwen2.5-3B-In...
2026.03
82.22
R1-Oracle
Backbone=Qwen2.5-3B-In...
2026.03
82
MemReward
Backbone=Qwen2.5-3B-In...
2026.03
81.78
MemReward
Backbone=Qwen2.5-1.5B-...
2026.03
79.33
R1-Oracle
Backbone=Qwen2.5-1.5B-...
2026.03
79.11
R1-p
Backbone=Qwen2.5-1.5B-...
2026.03
72.22
Feedback
Search any
task
Search any
task