Key Specifications
| Vendor | openai |
|---|
| Version | 4-vision-preview |
|---|
| Release Date | 2023-09-25 |
|---|
| Context Window | 128000 tokens |
|---|
| Input Modalities | text, image |
|---|
| Output Modalities | text |
|---|
| License | Proprietary |
|---|
| Documentation | https://platform.openai.com/docs/models |
|---|
Benchmark Performance
| Benchmark | Score | Unit | Evaluated At | Notes | Source |
|---|
| MMLU | 85 | % | 2023-09-25 | 5-shot | view |
| HUMANEVAL | 70.6 | pass@1 | 2023-09-25 | — | view |
| GSM8K | 84.5 | % | 2023-09-25 | 0-shot CoT | view |
| MATH | 49.7 | % | 2023-09-25 | 0-shot CoT | view |
| BBH | 75 | % | 2023-09-25 | 3-shot CoT | view |
| GPQA | 36.3 | % | 2023-09-25 | 0-shot | view |
| IFEVAL | 72.7 | % | 2023-09-25 | prompt_strict | view |
| ARC | 94.6 | % | 2023-09-25 | challenge | view |
| MUSR | 64.5 | % | 2023-09-25 | 0-shot | view |
| WINOGRANDE | 80.6 | % | 2023-09-25 | 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 2023-09-25
Compliance
- Data Residency: US
- SOC2: ✓
- HIPAA: ✓
- GDPR: ✓
- ISO 27001: ✓
GPT-4 Vision Preview
Przegląd modelu
OpenAI GPT-4 Vision 预览版, 支持图像输入理解, 128K 上下文, 多模态能力首次集成。
Podstawowe specyfikacje
| Dostawca | Wersja | Data wydania | Okno kontekstowe | Modalności wejściowe | Modalności wyjściowe | Licencja |
|---|
| Openai | 4-vision-preview | 2023-09-25 | 128K | text, image | text | Proprietary |
Wydajność benchmarków
| Benchmark | Wynik | Jednostka | Uwagi |
|---|
| MMLU (Massive Multitask Language Understanding) | 85.0 | % | 5-shot |
| HumanEval | 70.6 | pass@1 | — |
| GSM8K (Grade School Math 8K) | 84.5 | % | 0-shot CoT |
| MATH | 49.7 | % | 0-shot CoT |
| BBH (BIG-Bench Hard) | 75.0 | % | 3-shot CoT |
| GPQA | 36.3 | % | 0-shot |
| IFEval | 72.7 | % | prompt_strict |
| ARC | 94.6 | % | challenge |
| MUSR | 64.5 | % | 0-shot |
| WinoGrande | 80.6 | % | 0-shot |
Ceny
| Wejście | Wyjście | Odczyt pamięci podręcznej | Zapis pamięci podręcznej |
|---|
| — | — | — | — |
za milion tokenów
Mocne strony
- MMLU score 85.0, strong knowledge reasoning.
- 支持文本、图像、音频多模态输入。
Słabe strony
Przypadki użycia
- 代码生成与调试
- 视觉与图像理解
- Agent 工作流与工具调用
Referencje