Key Specifications
| Vendor | openai |
|---|
| Version | 4o-2024-08-06 |
|---|
| Release Date | 2024-08-06 |
|---|
| Context Window | 128000 tokens |
|---|
| Input Modalities | text, image, audio |
|---|
| Output Modalities | text, audio |
|---|
| License | Proprietary |
|---|
| Documentation | https://platform.openai.com/docs/models |
|---|
Benchmark Performance
| Benchmark | Score | Unit | Evaluated At | Notes | Source |
|---|
| MMLU | 87.6 | % | 2024-08-06 | 5-shot | view |
| HUMANEVAL | 85.1 | pass@1 | 2024-08-06 | — | view |
| GSM8K | 93.3 | % | 2024-08-06 | 0-shot CoT | view |
| MATH | 68.2 | % | 2024-08-06 | 0-shot CoT | view |
| BBH | 84.9 | % | 2024-08-06 | 3-shot CoT | view |
| GPQA | 62 | % | 2024-08-06 | 0-shot | view |
| IFEVAL | 85.5 | % | 2024-08-06 | prompt_strict | view |
| ARC | 95.9 | % | 2024-08-06 | challenge | view |
| MUSR | 62.9 | % | 2024-08-06 | 0-shot | view |
| WINOGRANDE | 87.7 | % | 2024-08-06 | 0-shot | view |
Pricing
| Tier | Price | Currency |
|---|
| Input | $2.5 / Mtok | USD |
| Output | $10 / Mtok | USD |
| Cache Read | $0 / Mtok | USD |
| Cache Write | $0 / Mtok | USD |
Source:
https://openai.com/api/pricing/
· as of 2024-08-06
Compliance
- Data Residency: US
- SOC2: ✓
- HIPAA: ✓
- GDPR: ✓
- ISO 27001: ✓
GPT-4o (2024-08-06)
Przegląd modelu
OpenAI GPT-4o 2024-08-06 快照版本, 价格降低 50%, 支持 Structured Outputs 结构化输出。
Podstawowe specyfikacje
| Dostawca | Wersja | Data wydania | Okno kontekstowe | Modalności wejściowe | Modalności wyjściowe | Licencja |
|---|
| Openai | 4o-2024-08-06 | 2024-08-06 | 128K | text, image, audio | text, audio | Proprietary |
Wydajność benchmarków
| Benchmark | Wynik | Jednostka | Uwagi |
|---|
| MMLU (Massive Multitask Language Understanding) | 87.6 | % | 5-shot |
| HumanEval | 85.1 | pass@1 | — |
| GSM8K (Grade School Math 8K) | 93.3 | % | 0-shot CoT |
| MATH | 68.2 | % | 0-shot CoT |
| BBH (BIG-Bench Hard) | 84.9 | % | 3-shot CoT |
| GPQA | 62.0 | % | 0-shot |
| IFEval | 85.5 | % | prompt_strict |
| ARC | 95.9 | % | challenge |
| MUSR | 62.9 | % | 0-shot |
| WinoGrande | 87.7 | % | 0-shot |
Ceny
| Wejście | Wyjście | Odczyt pamięci podręcznej | Zapis pamięci podręcznej |
|---|
| — | — | — | — |
za milion tokenów
Mocne strony
- MMLU score 87.6, strong knowledge reasoning.
- HumanEval 85.1, excellent code generation.
- GSM8K 93.3, robust math 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