Counterfactual Reasoning on CRASS
94.53Exact Match PerformanceGPT-4
Evaluation Results
| Method | Links | |
|---|---|---|
| GPT-4Setting=Zero-shot2023.11 | 94.53 | |
| Orca-1-13BSetting=Zero-shot2023.11 | 90.15 | |
| Orca 2-7BSetting=Zero-shot, System Message=Cautious2023.11 | 88.32 | |
| Orca 2-13BSetting=Zero-shot, System Message=Cautious2023.11 | 87.59 | |
| Orca 2-13BSetting=Zero-shot, System Message=Default2023.11 | 86.86 | |
| WizardLM-70BSetting=Zero-shot2023.11 | 86.13 | |
| ChatGPTSetting=Zero-shot2023.11 | 85.77 | |
| Orca 2-7BSetting=Zero-shot, System Message=Default2023.11 | 84.31 | |
| LLaMA-2-Chat-70BSetting=Zero-shot2023.11 | 74.82 | |
| WizardLM-13BSetting=Zero-shot2023.11 | 67.88 | |
| LLaMA-2-Chat-13BSetting=Zero-shot2023.11 | 61.31 |