跳转到主要内容

GPT-5.4 (low)

OpenAIGPTProprietary

描述

GPT-5.4 is OpenAI's most capable and efficient frontier model for professional work. It combines industry-leading coding capabilities with native computer-use, up to 1M tokens of context, full-resolution vision processing, tool search for large tool ecosystems, and improved reasoning across spreadsheets, presentations, and documents. It is the most token-efficient reasoning model in the GPT-5 series.

发布日期
2026-03-05
参数规模
上下文长度
1.1M
支持模态
file, image, text

能力雷达图

44
general
46
coding
87
reasoning
63
science估算
70
agents
85
multimodal

Science 在缺少专门科学评测时使用推理能力代理估算。

排行榜排名

领域#排名分数来源
智能体与工具18
68.0
LS
代码能力榜27
79.0
AA
通用能力榜57
77.0
AA
多模态榜10
89.0
LS
推理能力15
87.0
LS
科学能力23
80.0
AA

基准测试分数 (LLM Stats)

Agents

BrowseComp82.7%自报
Terminal-Bench 2.075.1%自报
OSWorld-Verified75.0%自报
MCP Atlas67.2%自报
SWE-Bench Pro57.7%自报
Finance Agent56.0%自报
Toolathlon54.6%自报

Biology

GPQA92.8%自报

Communication

Tau2 Telecom98.9%自报

General

MMMU-Pro81.2%自报

Long Context

Graphwalks parents >128k32.4%自报
Graphwalks BFS >128k21.4%自报

Math

FrontierMath47.6%自报
Humanity's Last Exam39.8%自报

Multimodal

OmniDocBench 1.589.1%自报

Reasoning

ARC-AGI93.7%自报
Graphwalks BFS <128k93.0%自报
Graphwalks parents <128k89.8%自报
ARC-AGI v273.3%自报

AA 评测指数

Intelligence Index
47.9
Coding Index
45.6
Gpqa
0.9
Tau2
0.7
Lcr
0.7
Ifbench
0.7
Scicode
0.5
Terminalbench Hard
0.4
Hle
0.3

LLM Stats 分类评分

Communication
100
Structured Output
90
Biology
90
Chemistry
90
Physics
90
Vision
80
General
80
Multimodal
80
Search
80
Spatial Reasoning
70
Tool Calling
70
Agents
70
Code
70
Reasoning
70
Finance
60
Long Context
40
Math
40
Healthcare
30

定价

输入价格$2.5 / 1M tokens
输出价格$15 / 1M tokens
混合价格(3:1)$5.625 / 1M tokens

速度

Tokens/秒67.1 tokens/s
首Token延迟1.85s
首回答延迟1.85s

可用提供商

(LS 内部计价单位)
提供商输入价格输出价格
OpenAI2.5M15.0M

外部链接