Knowledge Base QA Recommendation: Claude 3.5 Sonnet
Knowledge Base QA → Claude 3.5 Sonnet
Anwendungsfallübersicht
Claude 3.5 Sonnet by Anthropic is a recommended option for the Knowledge Base QA use case.
Empfohlene Modelle
| Rang | Anbieter | Kontextfenster | Score |
|---|
| #1 | Anthropic | 200K | 37/100 |
Leistungsanalyse
Benchmark-Leistung
| Benchmark | Ergebnis |
|---|
| MMLU | 88.7 |
| HUMANEVAL | 92.0 |
| GSM8K | 96.4 |
| MATH | 71.1 |
| BBH | 84.5 |
Stärken
- MMLU score 88.7, strong knowledge reasoning.
- HumanEval 92.0, excellent code generation.
- GSM8K 96.4, robust math reasoning.
- 上下文窗口 200K，支持长文本。
Anforderungen
- 需要 anthropic 的 API 密钥
- 输入长度须在 200K 上下文窗口内