Benchmark Performance
| Benchmark | Score | Unit | Evaluated At | Notes | Source |
|---|
| MMLU | 81.8 | % | 2023-11-06 | 5-shot | view |
| HUMANEVAL | 83.7 | pass@1 | 2023-11-06 | — | view |
| GSM8K | 85.4 | % | 2023-11-06 | 0-shot CoT | view |
| MATH | 52.1 | % | 2023-11-06 | 0-shot CoT | view |
| BBH | 80 | % | 2023-11-06 | 3-shot CoT | view |
| GPQA | 36.2 | % | 2023-11-06 | 0-shot | view |
| IFEVAL | 73.9 | % | 2023-11-06 | prompt_strict | view |
| ARC | 94.3 | % | 2023-11-06 | challenge | view |
| MUSR | 58.4 | % | 2023-11-06 | 0-shot | view |
| WINOGRANDE | 82 | % | 2023-11-06 | 0-shot | view |
Pricing
| Tier | Price | Currency |
|---|
| Input | $10 / Mtok | USD |
| Output | $30 / Mtok | USD |
| Cache Read | $0 / Mtok | USD |
| Cache Write | $0 / Mtok | USD |
Source:
https://openai.com/api/pricing/
· as of 2023-11-06
Compliance
- Data Residency: US
- SOC2: ✓
- HIPAA: ✓
- GDPR: ✓
- ISO 27001: ✓
GPT-4 1106 Preview
Aperçu du modèle
OpenAI GPT-4 1106 预览版, 128K 上下文, 改进函数调用与 JSON 模式, 适合结构化输出任务。
Spécifications principales
| Fournisseur | Version | Date de sortie | Fenêtre de contexte | Modalités d’entrée | Modalités de sortie | Licence |
|---|
| Openai | 4-1106-preview | 2023-11-06 | 128K | text | text | Proprietary |
| Benchmark | Score | Unité | Notes |
|---|
| MMLU (Massive Multitask Language Understanding) | 81.8 | % | 5-shot |
| HumanEval | 83.7 | pass@1 | — |
| GSM8K (Grade School Math 8K) | 85.4 | % | 0-shot CoT |
| MATH | 52.1 | % | 0-shot CoT |
| BBH (BIG-Bench Hard) | 80.0 | % | 3-shot CoT |
| GPQA | 36.2 | % | 0-shot |
| IFEval | 73.9 | % | prompt_strict |
| ARC | 94.3 | % | challenge |
| MUSR | 58.4 | % | 0-shot |
| WinoGrande | 82.0 | % | 0-shot |
Tarification
| Entrée | Sortie | Lecture cache | Écriture cache |
|---|
| — | — | — | — |
par million de jetons
Forces
- 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。
Faiblesses
Cas d’usage
- 代码生成与调试
- 长文档摘要
- Agent 工作流与工具调用
Références