Moral Judgment on Social Chemistry 101
32AccuracyGPT-5-mini
Evaluation Results
| Method | Links | |
|---|---|---|
| GPT-5-miniSamples per dataset=1002026.03 | 32 | |
| GPT-4oSamples per dataset=1002026.03 | 31 | |
| GPT-4o-miniSamples per dataset=1002026.03 | 31 | |
| o3-miniSamples per dataset=1002026.03 | 30.3 | |
| o4-miniSamples per dataset=1002026.03 | 30.2 | |
| GPT-5Samples per dataset=1002026.03 | 29.9 |