Discriminative Evaluation on CWQ (test)
92.88Binary AccuracyVicuna-1.5
Evaluation Results
| Method | Links | |
|---|---|---|
| Vicuna-1.5Size=33B, Prompting Strategy=Zero-shot CoT2024.02 | 92.88 | |
| Vicuna-1.5Size=33B, Prompting Strategy=Zero-shot2024.02 | 92.79 | |
| ChatGPTSize=175B, Prompting Strategy=Zero-shot CoT2024.02 | 90.17 | |
| MistralSize=7B, Prompting Strategy=Zero-shot CoT2024.02 | 89.88 | |
| ChatGPTSize=175B, Prompting Strategy=Zero-shot2024.02 | 89.86 | |
| QwenSize=14B, Prompting Strategy=Zero-shot CoT2024.02 | 88.86 | |
| QwenSize=14B, Prompting Strategy=Few-shot2024.02 | 88.81 | |
| QwenSize=14B, Prompting Strategy=Zero-shot2024.02 | 88.59 | |
| MistralSize=7B, Prompting Strategy=Zero-shot2024.02 | 87.59 | |
| ChatGPTSize=175B, Prompting Strategy=Few-shot2024.02 | 87.09 | |
| Vicuna-1.5Size=33B, Prompting Strategy=Few-shot2024.02 | 84.91 | |
| LLaMA2-ChatSize=70B, Prompting Strategy=Zero-shot CoT2024.02 | 80.71 | |
| ChatGPTSize=175B, Prompting Strategy=Few-shot CoT2024.02 | 80.15 | |
| QwenSize=7B, Prompting Strategy=Few-shot2024.02 | 79.64 | |
| LLaMA2-ChatSize=70B, Prompting Strategy=Zero-shot2024.02 | 77.96 | |
| QwenSize=7B, Prompting Strategy=Zero-shot CoT2024.02 | 76.13 | |
| QwenSize=14B, Prompting Strategy=Few-shot CoT2024.02 | 75.87 | |
| QwenSize=7B, Prompting Strategy=Zero-shot2024.02 | 74.76 | |
| QwenSize=7B, Prompting Strategy=Few-shot CoT2024.02 | 73.23 | |
| MistralSize=7B, Prompting Strategy=Few-shot CoT2024.02 | 69.98 | |
| Vicuna-1.5Size=33B, Prompting Strategy=Few-shot CoT2024.02 | 67.05 | |
| LLaMA2-ChatSize=70B, Prompting Strategy=Few-shot2024.02 | 56.99 | |
| MistralSize=7B, Prompting Strategy=Few-shot2024.02 | 56.91 | |
| LLaMA2-ChatSize=70B, Prompting Strategy=Few-shot CoT2024.02 | 47.76 |