Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Generation Quality on RedPajama Generation Quality Prefixes (test)
Loading...
32.4
Standard Prefix Count
Self-Improving Pretraining: RF-NLL (rollout vs. rewrite)
0.056
8.453
16.85
25.247
Jan 29, 2026
Standard Prefix Count
Unsafe Prefix Count
Updated 1mo ago
Evaluation Results
Method
Method
Links
Standard Prefix Count
Unsafe Prefix Count
Self-Improving Pretraining: RF-NLL (rollout vs. rewrite)
Pretraining Strategy=f...
2026.01
32.4
12.1
Self-Improving Pretraining: RF-NLL (suffix vs. rewrite)
Pretraining Strategy=f...
2026.01
5.3
25.8
Pretrain on Rewrites
Pretraining Strategy=f...
2026.01
1.6
2.4
Pretrain Baseline
Pretraining Strategy=f...
2026.01
1.3
2.4
Feedback
Search any
task
Search any
task