Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Dialogue Quality Calibration on PopAlign-Bench (test)
Loading...
8.69
Average Score
DiaSynth
4.8836
5.8718
6.86
7.8482
Jun 5, 2026
Average Score
Mean Absolute Deviation
Updated 1mo ago
Evaluation Results
Method
Method
Links
Average Score
Mean Absolute Deviation
DiaSynth
2026.06
8.69
1.77
PersonaLens
2026.06
8.49
1.57
ConceptPersona
2026.06
8.31
1.39
FaithfulPersona
2026.06
8.07
1.15
GroupPersona
2026.06
7.45
0.63
Reference
2026.06
6.92
0
ICL
2026.06
6.01
0.91
Interlocutor
2026.06
5.44
1.49
AutoPAL
2026.06
5.03
1.89
Feedback
Search any
task
Search any
task