Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Social Intelligence Assessment on SOTOPIA hard episodes (test)
Loading...
-0.02
SOC Score
DEMO-Qwen2-7B
-0.5192
-0.3896
-0.26
-0.1304
Dec 6, 2024
SOC Score
SEC Score
FIN Score
REL Score
KNO Score
GOA Score
BEL Score
Overall Score
Updated 4d ago
Evaluation Results
Method
Method
Links
SOC Score
SEC Score
FIN Score
REL Score
KNO Score
GOA Score
BEL Score
Overall Score
DEMO-Qwen2-7B
Backbone=Qwen2-7B, Met...
2024.12
-0.02
0
0.82
2.32
4.52
6.4
8.94
3.28
Qwen2-7B-Instruct
Backbone=Qwen2-7B, Var...
2024.12
-0.05
0
0.73
1.83
3.41
6.07
8.64
2.95
DEMO-Llama3.1-8B
Backbone=Llama3.1-8B,...
2024.12
-0.19
0
0.29
0.85
2.88
3.77
8.41
2.29
Llama3.1-8B-Instruct
Backbone=Llama3.1-8B,...
2024.12
-0.5
-0.01
-0.16
0.6
2.21
3.39
8.63
1.85
Feedback
Search any
task
Search any
task