Symbolic Reasoning on Coin Flip OOD (test)
65.7AccuracyAMPLIFY
Evaluation Results
| Method | Links | |
|---|---|---|
| AMPLIFYModel=GPT-3, Prompting Strategy=AMPLIFY2023.05 | 65.7 | |
| AMPLIFYModel=GPT-3.5, Prompting Strategy=AMPLIFY2023.05 | 65.3 | |
| GPT-3Model=GPT-3, Prompting Strategy=CoT2023.05 | 63.3 | |
| GPT-3.5Model=GPT-3.5, Prompting Strategy=CoT2023.05 | 61 | |
| GPT-3Model=GPT-3, Prompting Strategy=AO2023.05 | 54.7 | |
| GPT-3.5Model=GPT-3.5, Prompting Strategy=AO2023.05 | 52.9 |