GPT-5 (high)

OpenAIGPTProprietary

描述

GPT-5 is a flagship model from OpenAI designed for coding, reasoning, and agentic tasks across domains. It is optimized for coding and agentic tasks with higher reasoning capabilities and medium speed.

发布日期

2025-08-07

参数规模

—

上下文长度

400K

支持模态

image, text

能力雷达图

general

coding

reasoning

science

agents

multimodal

排行榜排名

领域	#排名	分数	来源
代码能力榜	212	64.0	AA
通用能力榜	85	69.0	AA
多模态榜	20	63.0	LS
科学能力	150	66.0	AA

基准测试分数 (LLM Stats)

(LLM Stats (zeroeval))

Chat

Multi-Challenge

69.6%自报

Tau2 Airline

62.6%自报

Communication

Tau2 Telecom

96.7%自报

Tau2 Retail

81.1%自报

General

MMLU

92.5%自报

Aider-Polyglot

88.0%自报

Internal API instruction following (hard)

64.0%自报

LongFact Objects

0.8%自报

LongFact Concepts

0.7%自报

Healthcare

HealthBench Hard

1.6%自报

Language

COLLIE

99.0%自报

Long Context

OpenAI-MRCR: 2 needle 128k

95.2%自报

OpenAI-MRCR: 2 needle 256k

86.8%自报

Math

AIME 2025

94.6%自报

HMMT 2025

93.3%自报

MATH

84.7%自报

FrontierMath

26.3%自报

Multimodal

VideoMMMU

84.6%自报

MMMU

84.2%自报

Reasoning

SWE-Lancer (IC-Diamond subset)

100.0%自报

HumanEvalOpenAI (2021)

93.4%自报

BrowseComp Long Context 128k

90.0%自报

BrowseComp Long Context 256k

88.8%自报

GPQANYU + Cohere + Anthropic (2023)

87.3%自报

CharXiv-R

81.1%自报

Graphwalks BFS <128k

78.3%自报

SWE-Bench Verified

74.9%自报

Graphwalks parents <128k

73.3%自报

BrowseCompOpenAI (2025)

54.9%自报

Humanity's Last Exam

24.8%自报

FActScoreMin et al. (NYU/UW, 2023)

1.0%自报

Vision

VideoMME w sub.

86.7%自报

MMMU-Pro

78.4%自报

ERQA

65.7%自报

AA 评测指数

(Artificial Analysis)

Math 500(OpenAI (2024), subset of Hendrycks et al. MATH (2021))

99.4

Aime(MAA (Mathematical Association of America))

95.7

Aime 25(MAA (Mathematical Association of America))

94.3

Math Index(Artificial Analysis)

94.3

Mmlu Pro(TIGER-Lab (Univ. of Waterloo, Toronto, CMU, 2024))

87.1

Gpqa(NYU + Cohere + Anthropic (2023))

85.4

Tau2(Sierra + U Toronto + Vector Institute (2025))

84.8

Livecodebench(UC Berkeley + MIT + Cornell (2024))

84.6

Lcr(Artificial Analysis)

78.2

Ifbench(Google Research (2023))

73.1

Coding Index(Artificial Analysis)

37.8

Terminalbench V2 1

35.2

Terminalbench Hard(Stanford × Laude Institute (2026))

32.6

Hle(Center for AI Safety + Scale AI (2025))

28.5

Intelligence Index(Artificial Analysis)

23.0

Tau Banking

22.1

LLM Stats 分类评分

(LLM Stats (zeroeval))

Spatial Reasoning

Vision

Reasoning

General

Language

100

Long Context

100

Writing

100

Legal

Physics

Finance

Biology

Chemistry

Code

Video

Multimodal

Communication

Tool Calling

Chat

Math

Frontend Development

Healthcare

Structured Output

Agents

定价

输入价格$1.25 / 1M tokens

输出价格$10 / 1M tokens

混合价格(3:1)$3.438 / 1M tokens

缓存读取价格$0.125 / 1M tokens

速度

Tokens/秒0.0

首Token延迟0.00s

首回答延迟0.00s

供应商价格排行

1 个供应商

供应商输入输出

1OpenAI主要

$1.25

$10

比较该模型在不同 API 供应商之间的定价。

外部链接

LLM Stats Artificial Analysis