Commonsense Morality on ETHICS Commonsense Morality (test)
99AccuracySKIG
Evaluation Results
| Method | Links | |
|---|---|---|
| SKIGModel=GPT-42024.05 | 99 | |
| I/OModel=GPT-42024.05 | 97 | |
| TEModel=GPT-3.5 TURBO2024.05 | 96 | |
| SKIGModel=GPT-3.5 TURBO2024.05 | 96 | |
| TEModel=GPT-42024.05 | 95 | |
| CoTModel=GPT-42024.05 | 94 | |
| SKIGModel=MISTRAL-7B2024.05 | 94 | |
| CoTModel=GPT-3.5 TURBO2024.05 | 92 | |
| TEModel=MISTRAL-7B2024.05 | 89 | |
| SKIGModel=DAVINCI2024.05 | 87 | |
| TEModel=DAVINCI2024.05 | 85 | |
| I/OModel=DAVINCI2024.05 | 82 | |
| I/OModel=GPT-3.5 TURBO2024.05 | 81 | |
| CoTModel=DAVINCI2024.05 | 75 | |
| CoTModel=MISTRAL-7B2024.05 | 67 | |
| I/OModel=MISTRAL-7B2024.05 | 66 | |
| SKIGModel=ADA2024.05 | 56 | |
| TEModel=BABBAGE2024.05 | 53 | |
| CoTModel=CURIE2024.05 | 52 | |
| SKIGModel=BABBAGE2024.05 | 51 | |
| I/OModel=CURIE2024.05 | 50 | |
| SKIGModel=CURIE2024.05 | 50 | |
| CoTModel=ADA2024.05 | 49 | |
| CoTModel=BABBAGE2024.05 | 48 | |
| I/OModel=BABBAGE2024.05 | 46 | |
| I/OModel=ADA2024.05 | 45 | |
| TEModel=CURIE2024.05 | 45 | |
| TEModel=ADA2024.05 | 41 |