📊 Showing 6 results | 📏 Metric: Accuracy
| Rank | Model | Paper | Accuracy | Date | Code |
|---|---|---|---|---|---|
| 1 | PaLM 540B (Self Improvement, Self Consistency) | Large Language Models Can Self-Improve | 83.00 | 2022-10-20 | - |
| 2 | PaLM 540B (Self Consistency) | Large Language Models Can Self-Improve | 78.20 | 2022-10-20 | - |
| 3 | PaLM 540B (Self Improvement, CoT Prompting) | Large Language Models Can Self-Improve | 76.20 | 2022-10-20 | - |
| 4 | PaLM 540B (Self Improvement, Standard-Prompting) | Large Language Models Can Self-Improve | 71.70 | 2022-10-20 | - |
| 5 | PaLM 540B (CoT Prompting) | Large Language Models Can Self-Improve | 70.60 | 2022-10-20 | - |
| 6 | PaLM 540B (Standard-Prompting) | Large Language Models Can Self-Improve | 60.00 | 2022-10-20 | - |