Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Human Evaluation on Hindi spoken dialogue (test)
Loading...
4.55
Naturalness
Human
4.082
4.2035
4.325
4.4465
Apr 25, 2026
Naturalness
Clarity
Human Preference
Model Preference
Tie Preference
Human-like Interaction
Appropriateness
Completion
Updated 1mo ago
Evaluation Results
Method
Method
Links
Naturalness
Clarity
Human Preference
Model Preference
Tie Preference
Human-like Interaction
Appropriateness
Completion
Human
Entity=Human
2026.04
4.55
4.05
-
-
-
-
-
-
Human-1
Entity=Model
2026.04
4.1
3.04
30
3.1
66.9
85
53
42
Feedback
Search any
task
Search any
task
