Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Post-RL Evaluation on BiGGen Bench
Loading...
63.7
Accuracy
MRRG
57.564
59.157
60.75
62.343
Jul 2, 2026
Accuracy
Updated 23d ago
Evaluation Results
Method
Method
Links
Accuracy
MRRG
2026.07
63.7
SVRG
Sub-reward (SR)=true
2026.07
62
Chasing the Tail
2026.07
61.1
SVRG
Sub-reward (SR)=false
2026.07
60
Base policy
Backbone=Qwen2.5-3B-In...
2026.07
57.8
Feedback
Search any
task
Search any
task