Benchmark Performance
| Benchmark | Score | Unit | Evaluated At | Notes | Source |
|---|
| MMLU | 86.3 | % | 2024-12-17 | 5-shot | view |
| HUMANEVAL | 85.3 | pass@1 | 2024-12-17 | — | view |
| GSM8K | 88.9 | % | 2024-12-17 | 0-shot CoT | view |
| MATH | 55.7 | % | 2024-12-17 | 0-shot CoT | view |
| BBH | 83.1 | % | 2024-12-17 | 3-shot CoT | view |
| GPQA | 57.5 | % | 2024-12-17 | 0-shot | view |
| IFEVAL | 82.2 | % | 2024-12-17 | prompt_strict | view |
| ARC | 96.8 | % | 2024-12-17 | challenge | view |
| MUSR | 71.8 | % | 2024-12-17 | 0-shot | view |
| WINOGRANDE | 86.7 | % | 2024-12-17 | 0-shot | view |
Pricing
| Tier | Price | Currency |
|---|
| Input | $15 / Mtok | USD |
| Output | $60 / Mtok | USD |
| Cache Read | $0 / Mtok | USD |
| Cache Write | $0 / Mtok | USD |
Source:
https://openai.com/api/pricing/
· as of 2024-12-17
Compliance
- Data Residency: US
- SOC2: ✓
- HIPAA: ✓
- GDPR: ✓
- ISO 27001: ✓
o1
Visão geral do modelo
OpenAI o1 正式版推理模型, 200K 上下文, 强化链式思维推理, 在数学竞赛与编程竞赛上达到顶尖水平。
Especificações principais
| Fornecedor | Versão | Data de lançamento | Janela de contexto | Modalidades de entrada | Modalidades de saída | Licença |
|---|
| Openai | o1 | 2024-12-17 | 200K | text | text | Proprietary |
Desempenho em benchmarks
| Benchmark | Pontuação | Unidade | Notas |
|---|
| MMLU (Massive Multitask Language Understanding) | 86.3 | % | 5-shot |
| HumanEval | 85.3 | pass@1 | — |
| GSM8K (Grade School Math 8K) | 88.9 | % | 0-shot CoT |
| MATH | 55.7 | % | 0-shot CoT |
| BBH (BIG-Bench Hard) | 83.1 | % | 3-shot CoT |
| GPQA | 57.5 | % | 0-shot |
| IFEval | 82.2 | % | prompt_strict |
| ARC | 96.8 | % | challenge |
| MUSR | 71.8 | % | 0-shot |
| WinoGrande | 86.7 | % | 0-shot |
Preços
| Entrada | Saída | Leitura de cache | Escrita de cache |
|---|
| — | — | — | — |
por milhão de tokens
Pontos fortes
- MMLU score 86.3, strong knowledge reasoning.
- HumanEval 85.3, excellent code generation.
- GSM8K 88.9, robust math reasoning.
Pontos fracos
Casos de uso
Referências