Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Cultural Alignment on United States survey 1.0 (test)
Loading...
65.95
Soft Metric
GPT-3.5
50.5268
54.5309
58.535
62.5391
Feb 20, 2024
Soft Metric
Hard Metric
Soft Alignment Difference (En-Ar)
Updated 4d ago
Evaluation Results
Method
Method
Links
Soft Metric
Hard Metric
Soft Alignment Difference (En-Ar)
GPT-3.5
Prompting language=Eng...
2024.02
65.95
40.22
2.18
LLAMA-2-Chat
Prompting language=Eng...
2024.02
63.9
37.4
1.61
GPT-3.5
Prompting language=Arabic
2024.02
63.77
38.36
-
LLAMA-2-Chat
Prompting language=Arabic
2024.02
62.29
36.03
-
mT0-XXL
Prompting language=Arabic
2024.02
57.75
34.51
-4.55
AceGPT-Chat
Prompting language=Eng...
2024.02
54.55
29.94
3.43
mT0-XXL
Prompting language=Eng...
2024.02
53.2
28.3
-
AceGPT-Chat
Prompting language=Arabic
2024.02
51.12
25.45
-
Feedback
Search any
task
Search any
task