Multi-step Planning Recommendation: GPT-4
Multi-step Planning → GPT-4
Kullanım Senaryosu Genel Bakışı
GPT-4 by Openai is a recommended option for the Multi-step Planning use case.
Önerilen Modeller
| Sıralama | Satıcı | Bağlam Penceresi | Score |
|---|
| #9 | Openai | 8K | 37/100 |
| Benchmark | Puan |
|---|
| MMLU | 85.8 |
| HUMANEVAL | 77.6 |
| GSM8K | 91.7 |
| MATH | 43.9 |
| BBH | 80.9 |
| GPQA | 39.2 |
Güçlü Yönler
- MMLU score 85.8, strong knowledge reasoning.
- GSM8K 91.7, robust math reasoning.
Gereksinimler
- 需要 openai 的 API 密钥
- 输入长度须在 8K 上下文窗口内