Ruin Names on Ruin Names (test)
78.6AccuracyAMPLIFY
Evaluation Results
| Method | Links | |
|---|---|---|
| AMPLIFYModel=GPT-3, Prompting Strategy=AMPLIFY2023.05 | 78.6 | |
| Human-RaterModel=Human, Prompting Strategy=Average2023.05 | 77.7 | |
| AMPLIFYModel=GPT-3.5, Prompting Strategy=AMPLIFY2023.05 | 77.5 | |
| SOTAModel=N/A, Prompting Strategy=N/A2023.05 | 72.8 | |
| GPT-3.5Model=GPT-3.5, Prompting Strategy=AO2023.05 | 69.6 | |
| GPT-3Model=GPT-3, Prompting Strategy=AO2023.05 | 64 | |
| GPT-3Model=GPT-3, Prompting Strategy=CoT2023.05 | 62.9 | |
| GPT-3.5Model=GPT-3.5, Prompting Strategy=CoT2023.05 | 62.9 | |
| RandomModel=N/A, Prompting Strategy=Random Choice2023.05 | 25 |