Moral Judgment on ETHICS
61Accuracy (ETHICS)GPT-4o-mini
Evaluation Results
| Method | Links | |
|---|---|---|
| GPT-4o-miniSamples per dataset=1002026.03 | 61 | |
| GPT-5-miniSamples per dataset=1002026.03 | 61 | |
| o4-miniSamples per dataset=1002026.03 | 60.6 | |
| GPT-4oSamples per dataset=1002026.03 | 55 | |
| o3-miniSamples per dataset=1002026.03 | 53.1 | |
| GPT-5Samples per dataset=1002026.03 | 49 |