GPT-4 Vision Preview: Complete Benchmark Performance Guide

openai 4-vision-preview 2023-09-25 Proprietary

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

Key Specifications

Vendoropenai
Version4-vision-preview
Release Date2023-09-25
Context Window128000 tokens
Input Modalitiestext, image
Output Modalitiestext
LicenseProprietary
Documentationhttps://platform.openai.com/docs/models

Benchmark Performance

BenchmarkScoreUnitEvaluated AtNotesSource
MMLU85%2023-09-255-shotview
HUMANEVAL70.6pass@12023-09-25—view
GSM8K84.5%2023-09-250-shot CoTview
MATH49.7%2023-09-250-shot CoTview
BBH75%2023-09-253-shot CoTview
GPQA36.3%2023-09-250-shotview
IFEVAL72.7%2023-09-25prompt_strictview
ARC94.6%2023-09-25challengeview
MUSR64.5%2023-09-250-shotview
WINOGRANDE80.6%2023-09-250-shotview

Pricing

TierPriceCurrency
Input$10 / MtokUSD
Output$30 / MtokUSD
Cache Read$0 / MtokUSD
Cache Write$0 / MtokUSD

Source: https://openai.com/api/pricing/ · as of 2023-09-25

Compliance

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

GPT-4 Vision Preview

Tổng quan mô hình

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。

Thông số kỹ thuật cốt lõi

Nhà cung cấpPhiên bảnNgày phát hànhCửa sổ ngữ cảnhPhương thức đầu vàoPhương thức đầu raGiấy phép
Openai4-vision-preview2023-09-25128Ktext, imagetextProprietary

Hiệu suất benchmark

BenchmarkĐiểmĐơn vịGhi chú
MMLU (Massive Multitask Language Understanding)85.0%5-shot
HumanEval70.6pass@1—
GSM8K (Grade School Math 8K)84.5%0-shot CoT
MATH49.7%0-shot CoT
BBH (BIG-Bench Hard)75.0%3-shot CoT
GPQA36.3%0-shot
IFEval72.7%prompt_strict
ARC94.6%challenge
MUSR64.5%0-shot
WinoGrande80.6%0-shot

Giá

Đầu vàoĐầu raĐọc bộ nhớ đệmGhi bộ nhớ đệm
————

mỗi triệu token

Điểm mạnh

  • MMLU score 85.0, strong knowledge reasoning.
  • 支持文本、图像、音频多模态输入。

Điểm yếu

  • 闭源专有模型，不支持自托管。

Trường hợp sử dụng

  • 代码生成与调试
  • 视觉与图像理解
  • Agent 工作流与工具调用

Tham chiếu