Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Turn-taking decision on RolePlayConv zero-shot (test)
Loading...
79
Precision
ModeratorLM-Think
12.44
29.72
47
64.28
Jun 11, 2026
Precision
Recall
F1-score
Macro Accuracy
False Positive Rate (FPR)
Reactive Miss Rate
Updated 1mo ago
Evaluation Results
Method
Method
Links
Precision
Recall
F1-score
Macro Accuracy
False Positive Rate (FPR)
Reactive Miss Rate
ModeratorLM-Think
Role conditioning=true...
2026.06
79
82
79
91
3
3
ModeratorLM
Role conditioning=true...
2026.06
71
57
61
76
5
14
MP-Baseline
Role conditioning=fals...
2026.06
40
48
42
67
14
-
Moshi
Role conditioning=fals...
2026.06
15
34
21
50
47
-
Feedback
Search any
task
Search any
task