GPT-4o mini: Complete Benchmark Performance Guide

openai 4o-mini 2024-07-18 Proprietary

In-depth analysis of GPT-4o mini performance on MMLU, HumanEval, GSM8K, MATH, BBH benchmarks, including pricing and use cases.

Key Specifications

Vendoropenai
Version4o-mini
Release Date2024-07-18
Context Window128000 tokens
Input Modalitiestext, image
Output Modalitiestext
LicenseProprietary
Documentationhttps://platform.openai.com/docs/models

Benchmark Performance

BenchmarkScoreUnitEvaluated AtNotesSource
MMLU79.7%2024-07-185-shotview
HUMANEVAL78pass@12024-07-18—view
GSM8K75.1%2024-07-180-shot CoTview
MATH51.8%2024-07-180-shot CoTview
BBH70.3%2024-07-183-shot CoTview
GPQA42.6%2024-07-180-shotview
IFEVAL67.9%2024-07-18prompt_strictview
ARC93.9%2024-07-18challengeview
MUSR53.1%2024-07-180-shotview
WINOGRANDE79.6%2024-07-180-shotview

Pricing

TierPriceCurrency
Input$0.15 / MtokUSD
Output$0.6 / MtokUSD
Cache Read$0 / MtokUSD
Cache Write$0 / MtokUSD

Source: https://openai.com/api/pricing/ · as of 2024-07-18

Compliance

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

GPT-4o mini

모델 개요

OpenAI 经济型多模态模型, 128K 上下文, 支持文本与图像输入, 平衡成本与性能, 适合大规模部署。

핵심 사양

공급업체버전출시일컨텍스트 창입력 모달리티출력 모달리티라이선스
Openai4o-mini2024-07-18128Ktext, imagetextProprietary

벤치마크 성능

벤치마크점수단위비고
MMLU (Massive Multitask Language Understanding)79.7%5-shot
HumanEval78.0pass@1—
GSM8K (Grade School Math 8K)75.1%0-shot CoT
MATH51.8%0-shot CoT
BBH (BIG-Bench Hard)70.3%3-shot CoT
GPQA42.6%0-shot
IFEval67.9%prompt_strict
ARC93.9%challenge
MUSR53.1%0-shot
WinoGrande79.6%0-shot

가격

입력출력캐시 읽기캐시 쓰기
————

백만 토큰당

강점

  • 支持文本、图像、音频多模态输入。

약점

  • 闭源专有模型，不支持自托管。

사용 사례

  • 代码生成与调试
  • 视觉与图像理解

참고문헌