Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Human Evaluation on Human Evaluation Set (test)
Loading...
0.65
Win Rate
LongDPO
0.61568
0.62459
0.6335
0.64241
Feb 4, 2025
Win Rate
Tie Rate
Lose Rate
Updated 4d ago
Evaluation Results
Method
Method
Links
Win Rate
Tie Rate
Lose Rate
LongDPO
Criteria=Diversity
2025.02
0.65
0.083
0.267
LongDPO
Criteria=Consistency
2025.02
0.617
0.167
0.216
LongDPO
Criteria=Informative
2025.02
0.617
0.067
0.316
Feedback
Search any
task
Search any
task