Question Answering on StrQA
84.45AccuracyACPS
Evaluation Results
| Method | Links | |
|---|---|---|
| ACPSModel=GPT-3.5-turbo2026.01 | 84.45 | |
| CPModel=GPT-3.5-turbo2026.01 | 73.97 | |
| ACPSModel=LLaMA-32026.01 | 73.03 | |
| CoT-SCModel=GPT-3.5-turbo2026.01 | 72.83 | |
| CPModel=LLaMA-32026.01 | 72.1 | |
| CADModel=GPT-3.5-turbo2026.01 | 71.79 | |
| DeCoTModel=LLaMA-32026.01 | 70.95 | |
| DeCoTModel=GPT-3.5-turbo2026.01 | 70.2 | |
| CADModel=LLaMA-32026.01 | 69.23 | |
| ACPSModel=Ministral-3B2026.01 | 67.8 | |
| ICLModel=GPT-3.5-turbo2026.01 | 67.62 | |
| CoT-SCModel=LLaMA-32026.01 | 64.29 | |
| SoTModel=GPT-3.5-turbo2026.01 | 59.8 | |
| CoTModel=GPT-3.5-turbo2026.01 | 58.83 | |
| ICLModel=LLaMA-32026.01 | 56.91 | |
| CPModel=Ministral-3B2026.01 | 55.56 | |
| CoT-SCModel=Ministral-3B2026.01 | 55.1 | |
| CADModel=Ministral-3B2026.01 | 54.24 | |
| DeCoTModel=Ministral-3B2026.01 | 53.15 | |
| CoTModel=LLaMA-32026.01 | 52.8 | |
| SoTModel=Ministral-3B2026.01 | 52.63 | |
| SoTModel=LLaMA-32026.01 | 52.04 | |
| CoTModel=Ministral-3B2026.01 | 51.72 | |
| ICLModel=Ministral-3B2026.01 | 45.34 |