Arithmetic Reasoning 벤치마크
Arithmetic Reasoning on MultiArith
| Rank | Model | Accuracy | Paper | Code | Year |
|---|---|---|---|---|---|
| 1 | Text-davinci-002 (175B)(zero-shot-cot) | 78.7 | Large Language Models are Zero-Shot Reasoners | kojima-takeshi188/zero_shot_cot · skytliang/multi-agents-debate · zongqianwu/st-cot · +1 | 2022 |
| 2 | Text-davinci-002 (175B) (zero-shot) | 17.7 | Large Language Models are Zero-Shot Reasoners | kojima-takeshi188/zero_shot_cot · skytliang/multi-agents-debate · zongqianwu/st-cot · +1 | 2022 |