Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Open-domain Conversation on Human-bot Chat
Loading...
1.92
Coherence
PLATO-XL (Diamante)
1.14
1.3425
1.545
1.7475
Aug 30, 2022
Coherence
Informativeness
Safety
Engagingness
Updated 3mo ago
Evaluation Results
Method
Method
Links
Coherence
Informativeness
Safety
Engagingness
PLATO-XL (Diamante)
2022.08
1.92
1.91
1.98
1.9
Tmall Genie
2022.08
1.58
1.51
1.78
1.25
Xiao AI
2022.08
1.57
1.54
1.88
1.2
XiaoIce
2022.08
1.54
1.49
1.79
1.15
Siri
2022.08
1.17
1.13
1.42
0.75
Feedback
Search any
task
Search any
task