Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Emotional Support Dialogue on Sentient Eval
Loading...
65
Win Rate (vs. PRINC.)
UKA
57.72
59.61
61.5
63.39
May 28, 2026
Win Rate (vs. PRINC.)
Fleiss' Kappa (vs. PRINC.)
Win Rate (vs. Prompt)
Fleiss' Kappa (vs. Prompt)
Updated 5d ago
Evaluation Results
Method
Method
Links
Win Rate (vs. PRINC.)
Fleiss' Kappa (vs. PRINC.)
Win Rate (vs. Prompt)
Fleiss' Kappa (vs. Prompt)
UKA
Backbone=Qwen3-235B
2026.05
65
0.475
58
0.528
UKA
Backbone=Seed-36B
2026.05
58
0.581
45
0.499
Feedback
Search any
task
Search any
task
