Knowledge Base QA Recommendation: GPT-4 1106 Preview
Knowledge Base QA → GPT-4 1106 Preview
Ikhtisar Kasus Penggunaan
GPT-4 1106 Preview by Openai is a recommended option for the Knowledge Base QA use case.
Model Rekomendasi
| Peringkat | Vendor | Jendela Konteks | Score |
|---|
| #10 | Openai | 128K | 36/100 |
Analisis Kinerja
Kinerja Benchmark
| Benchmark | Skor |
|---|
| MMLU | 81.8 |
| HUMANEVAL | 83.7 |
| GSM8K | 85.4 |
| MATH | 52.1 |
| BBH | 80.0 |
| GPQA | 36.2 |
Kelebihan
- MMLU score 81.8, strong knowledge reasoning.
- HumanEval 83.7, excellent code generation.
- GSM8K 85.4, robust math reasoning.
- 上下文窗口 128K,支持长文本。
Persyaratan
- 需要 openai 的 API 密钥
- 输入长度须在 128K 上下文窗口内