Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Conversation Evaluation on CRSArena-Eval Dial-level
Loading...
0.913
Pearson r
FACE
-0.16132
0.11759
0.3965
0.67541
Jun 11, 2026
Pearson r
Spearman ρ
Updated 1mo ago
Evaluation Results
Method
Method
Links
Pearson r
Spearman ρ
FACE
2026.06
0.913
0.837
G-Eval
type=reference-free
2026.06
0.893
0.83
LLMDirect
type=reference-free
2026.06
0.872
0.799
Distinct-3
n-gram=3
2026.06
0.665
0.78
Distinct-4
n-gram=4
2026.06
0.609
0.76
iEvaLMattr
mode=attr
2026.06
0.553
0.553
iEvaLMfree
mode=free
2026.06
0.232
0.232
R@10
type=reference-based
2026.06
-0.111
0.071
R@1
type=reference-based
2026.06
-0.12
0.081
Feedback
Search any
task
Search any
task