Key Specifications

Vendoropenai
Versiono1
Release Date2024-12-17
Context Window200000 tokens
Input Modalitiestext
Output Modalitiestext
LicenseProprietary
Documentationhttps://platform.openai.com/docs/models

Benchmark Performance

BenchmarkScoreUnitEvaluated AtNotesSource
MMLU86.3%2024-12-175-shotview
HUMANEVAL85.3pass@12024-12-17view
GSM8K88.9%2024-12-170-shot CoTview
MATH55.7%2024-12-170-shot CoTview
BBH83.1%2024-12-173-shot CoTview
GPQA57.5%2024-12-170-shotview
IFEVAL82.2%2024-12-17prompt_strictview
ARC96.8%2024-12-17challengeview
MUSR71.8%2024-12-170-shotview
WINOGRANDE86.7%2024-12-170-shotview

Pricing

TierPriceCurrency
Input$15 / MtokUSD
Output$60 / MtokUSD
Cache Read$0 / MtokUSD
Cache Write$0 / MtokUSD

Source: https://openai.com/api/pricing/ · as of 2024-12-17

Compliance

  • Data Residency: US
  • SOC2: ✓
  • HIPAA: ✓
  • GDPR: ✓
  • ISO 27001: ✓

o1

모델 개요

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。

핵심 사양

공급업체버전출시일컨텍스트 창입력 모달리티출력 모달리티라이선스
Openaio12024-12-17200KtexttextProprietary

벤치마크 성능

벤치마크점수단위비고
MMLU (Massive Multitask Language Understanding)86.3%5-shot
HumanEval85.3pass@1
GSM8K (Grade School Math 8K)88.9%0-shot CoT
MATH55.7%0-shot CoT
BBH (BIG-Bench Hard)83.1%3-shot CoT
GPQA57.5%0-shot
IFEval82.2%prompt_strict
ARC96.8%challenge
MUSR71.8%0-shot
WinoGrande86.7%0-shot

가격

입력출력캐시 읽기캐시 쓰기

백만 토큰당

강점

  • MMLU score 86.3, strong knowledge reasoning.
  • HumanEval 85.3, excellent code generation.
  • GSM8K 88.9, robust math reasoning.

약점

  • 闭源专有模型,不支持自托管。

사용 사례

  • 代码生成与调试
  • Agent 工作流与工具调用

참고문헌

  • o1 문서
  • 출시일: 2024-12-17
  • 공급업체: Openai