跳轉到主要內容

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.

發布日期
2026-03-05
參數規模
—
上下文長度
1.1M
支援模態
image, pdf, text

能力雷達圖

60
general
60
coding
60
reasoning
77
science估算
70
agents
85
multimodal

缺少專門科學評測時,Science 由 LLM Stats 科學得分或推理能力估算。

排行榜排名

領域#排名分數來源
智慧體能力模型榜67
48.0
LS
多模態榜56
56.0
LS

基準測試分數 (LLM Stats)

(LLM Stats (zeroeval))

Agents

Finance Agent56.0%自報
Toolathlon54.6%自報

Code

FrontierSWE54.0%
DeepSWE 1.152.0%

Communication

Tau2 Telecom98.9%自報

Legal

Legal Agent Benchmark0.4%

Math

LiveBench80.3%
FrontierMath47.6%自報

Multimodal

OSWorld-Verified75.0%自報

Reasoning

ARC-AGI93.7%自報
Graphwalks BFS <128k93.0%自報
GPQANYU + Cohere + Anthropic (2023)92.8%自報
Graphwalks parents <128k89.8%自報
BrowseCompOpenAI (2025)82.7%自報
Terminal-Bench 2.0Stanford × Laude Institute (2026)75.1%自報
ARC-AGI v273.3%自報
MCP Atlas67.2%自報
SWE-Bench ProPrinceton NLP (2024)57.7%自報
Humanity's Last Exam39.8%自報
Graphwalks parents >128k32.4%自報
Graphwalks BFS >128k21.4%自報

Vision

OmniDocBench 1.589.1%自報
MMMU-Pro81.2%自報

AA 評測指數

(Artificial Analysis)

暫無 AA 評測資料

LLM Stats 分類評分

(LLM Stats (zeroeval))
Communication
100
Physics
90
Structured Output
90
Biology
90
Chemistry
90
Multimodal
80
Search
80
Vision
80
Reasoning
70
Spatial Reasoning
70
Tool Calling
70
Math
60
Finance
60
General
60
Agents
60
Code
60
Long Context
40
Healthcare
30
Legal
0

定價

輸入價格$2.5 / 1M tokens
輸出價格$15 / 1M tokens
混合價格(3:1)$5.625 / 1M tokens
快取讀取價格$0.25 / 1M tokens

速度

Tokens/秒59.4
首Token延遲2.77s
首回答延遲2.77s

供應商價格排行

供應商價格排行

1 個供應商

供應商輸入輸出
1OpenAI主要
$2.5
$15

比較該模型在不同 API 供應商之間的定價。

外部連結