Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Preference Evaluation on HH-Harmless
Loading...
60
Win Rate
DLMA-13B
40.24
45.37
50.5
55.63
Feb 19, 2024
Win Rate
Loss Rate
Tie Rate
Updated 4d ago
Evaluation Results
Method
Method
Links
Win Rate
Loss Rate
Tie Rate
DLMA-13B
Comparison Baseline=Ll...
2024.02
60
15
25
DLMA-7B
Comparison Baseline=RL...
2024.02
59
21
20
DLMA-7B
Comparison Baseline=Ll...
2024.02
58
19
23
DLMA-13B
Comparison Baseline=CD...
2024.02
55
16
29
DLMA-13B
Comparison Baseline=RL...
2024.02
52
14
34
DLMA-7B
Comparison Baseline=CD-7B
2024.02
51
22
27
DLMA-13B
Comparison Baseline=RL...
2024.02
49
20
31
DLMA-7B
Comparison Baseline=RL...
2024.02
41
27
32
Feedback
Search any
task
Search any
task