Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Moral Judgment on ETHICS
Loading...
61
Accuracy (ETHICS)
GPT-4o-mini
48.52
51.76
55
58.24
Mar 16, 2026
Accuracy (ETHICS)
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy (ETHICS)
GPT-4o-mini
Samples per dataset=100
2026.03
61
GPT-5-mini
Samples per dataset=100
2026.03
61
o4-mini
Samples per dataset=100
2026.03
60.6
GPT-4o
Samples per dataset=100
2026.03
55
o3-mini
Samples per dataset=100
2026.03
53.1
GPT-5
Samples per dataset=100
2026.03
49
Feedback
Search any
task
Search any
task