Multi-step Planning Recommendation: o1
Multi-step Planning → o1
사용 사례 개요
o1 by Openai is a recommended option for the Multi-step Planning use case.
추천 모델
| 순위 | 공급업체 | 컨텍스트 창 | Score |
|---|---|---|---|
| #7 | Openai | 200K | 37/100 |
성능 분석
벤치마크 성능
| 벤치마크 | 점수 |
|---|---|
| MMLU | 86.3 |
| HUMANEVAL | 85.3 |
| GSM8K | 88.9 |
| MATH | 55.7 |
| BBH | 83.1 |
| GPQA | 57.5 |
강점
- MMLU score 86.3, strong knowledge reasoning.
- HumanEval 85.3, excellent code generation.
- GSM8K 88.9, robust math reasoning.
요구사항
- 需要 openai 的 API 密钥
- 输入长度须在 200K 上下文窗口内