Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Dialogue Evaluation on ACUTE-Eval Human-Chat (test)
Loading...
75
Engagingness
BlenderBot
23
36.5
50
63.5
May 5, 2021
Engagingness
Humanness
Updated 4d ago
Evaluation Results
Method
Method
Links
Engagingness
Humanness
BlenderBot
Parameters=2.7B, Refer...
2021.05
75
65
BlenderBot
Parameters=2.7B, Evalu...
2021.05
72
68
Meena
Evaluation Toolkit=LEG...
2021.05
28
32
Meena
Reference Study=Roller...
2021.05
25
35
Feedback
Search any
task
Search any
task