Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Dialogue Evaluation on Amazon Topical-Chat
Loading...
0.806
Naturalness (Pearson r)
MILE-RefHumEval
0.53872
0.60811
0.6775
0.74689
Feb 10, 2026
Naturalness (Pearson r)
Naturalness (Spearman ρ)
Coherence (Pearson r)
Coherence (Spearman ρ)
Engagingness (Pearson r)
Engagingness (Spearman ρ)
Groundedness (Pearson r)
Groundedness (Spearman ρ)
Average Score (Pearson r)
Average Score (Spearman ρ)
Updated 1mo ago
Evaluation Results
Method
Method
Links
Naturalness (Pearson r)
Naturalness (Spearman ρ)
Coherence (Pearson r)
Coherence (Spearman ρ)
Engagingness (Pearson r)
Engagingness (Spearman ρ)
Groundedness (Pearson r)
Groundedness (Spearman ρ)
Average Score (Pearson r)
Average Score (Spearman ρ)
MILE-RefHumEval
2026.02
0.806
0.75
0.805
0.739
0.746
0.683
0.863
0.813
0.692
0.612
G-Eval
2026.02
0.549
0.565
0.594
0.605
0.627
0.631
0.531
0.551
0.575
0.588
Feedback
Search any
task
Search any
task