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
image, pdf, text

能力雷达图

37
general
50
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
代码能力榜41
79.0
AA
通用能力榜77
70.0
AA
科学能力33
76.0
AA

基准测试分数 (LLM Stats)

Agents

GDPval-AA1429.00 / 3000自报
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
FrontierSWE54.0%自报
Legal Agent Benchmark0.4%自报

Biology

GPQA92.8%自报

Communication

Tau2 Telecom98.9%自报

General

MMMU-Pro81.2%自报
LiveBench80.3%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
39.1
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

Finance
100
Legal
100
General
100
Agents
100
Reasoning
63
Communication
100
Physics
90
Structured Output
90
Biology
90
Chemistry
90
Multimodal
80
Search
80
Vision
80
Spatial Reasoning
70
Tool Calling
70
Math
60
Code
60
Long Context
40
Healthcare
30

定价

输入价格$2.625 / 1M tokens
输出价格$15.75 / 1M tokens
混合价格(3:1)$5.906 / 1M tokens
缓存读取价格$0.25 / 1M tokens

速度

Tokens/秒133.1
首Token延迟1.11s
首回答延迟1.11s

供应商价格排行

供应商价格排行

1 个供应商

供应商输入输出
1OpenAI
$0
$0.00002

比较该模型在不同 API 供应商之间的定价。

外部链接