Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Multi-party cognitive stimulation dialogue on Real-world Cognitive Stimulation Dialogue dataset (test)
Loading...
75
Win Rate
GCSD-3b
41.72
50.36
59
67.64
Mar 1, 2026
Win Rate
Loss Rate
Tie Rate
Updated 1mo ago
Evaluation Results
Method
Method
Links
Win Rate
Loss Rate
Tie Rate
GCSD-3b
baseline_comparison=ERNIE
2026.03
75
10
15
GCSD-3b
baseline_comparison=GL...
2026.03
73
12
15
GCSD-3b
baseline_comparison=Do...
2026.03
60
23
17
GCSD-3b
baseline_comparison=Ch...
2026.03
58
27
15
GCSD-3b
baseline_comparison=LL...
2026.03
58
34
8
GCSD-3b
baseline_comparison=Qw...
2026.03
55
29
16
GCSD-3b
baseline_comparison=GP...
2026.03
50
39
11
GCSD-3b
baseline_comparison=De...
2026.03
43
40
17
Feedback
Search any
task
Search any
task