Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Generation Quality on OSE
Loading...
40.26
PPL
Prompt-steer
35.872
65.491
95.11
124.729
May 28, 2026
PPL
BERTScore
Updated 5d ago
Evaluation Results
Method
Method
Links
PPL
BERTScore
Prompt-steer
Model=Llada-8b
2026.05
40.26
0.185
DLM-SWAI
Model=Llada-8b
2026.05
43.1
0.193
DLM-SWAI
Model=Dream-7b
2026.05
47.43
0.237
Activation-steer
Model=Llada-8b
2026.05
90.04
0.186
Prompt-steer
Model=Dream-7b
2026.05
92.37
0.08
Activation-steer
Model=Dream-7b
2026.05
149.96
0.178
Feedback
Search any
task
Search any
task