Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Prompt Refinement on Unseen Systems Aggregated (test)
Loading...
1.68
Relevance
PRIP
1.5136
1.5568
1.6
1.6432
Jun 28, 2024
Relevance
Updated 4d ago
Evaluation Results
Method
Method
Links
Relevance
PRIP
Refiner=PRIP
2024.06
1.68
w/o refine
Refinement=None
2024.06
1.67
Rew-Log+RL
Refiner=Rew-Log+RL
2024.06
1.67
Rew-Syn+RL
Refiner=Rew-Syn+RL
2024.06
1.62
PromptistRL
Refiner=PromptistRL
2024.06
1.52
Feedback
Search any
task
Search any
task