List your company

Moral Judgment on Social Chemistry 101

32AccuracyGPT-5-mini
29.81630.38330.9531.517Mar 16, 2026

Evaluation results

MethodLinks
GPT-5-miniSamples per dataset=1002026.0332
GPT-4oSamples per dataset=1002026.0331
GPT-4o-miniSamples per dataset=1002026.0331
o3-miniSamples per dataset=1002026.0330.3
o4-miniSamples per dataset=1002026.0330.2
GPT-5Samples per dataset=1002026.0329.9