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
37
general
50
coding
87
reasoning
63
science估算
70
agents
85
multimodal
Science 在缺少專門科學評測時使用推理能力代理估算。
排行榜排名
基準測試分數 (LLM Stats)
Agents
GDPval-AA
1429.00 / 3000自報
BrowseComp
82.7%自報
Terminal-Bench 2.0
75.1%自報
OSWorld-Verified
75.0%自報
MCP Atlas
67.2%自報
SWE-Bench Pro
57.7%自報
Finance Agent
56.0%自報
Toolathlon
54.6%自報
FrontierSWE
54.0%自報
Legal Agent Benchmark
0.4%自報
Biology
GPQA
92.8%自報
Communication
Tau2 Telecom
98.9%自報
General
MMMU-Pro
81.2%自報
LiveBench
80.3%自報
Long Context
Graphwalks parents >128k
32.4%自報
Graphwalks BFS >128k
21.4%自報
Math
FrontierMath
47.6%自報
Humanity's Last Exam
39.8%自報
Multimodal
OmniDocBench 1.5
89.1%自報
Reasoning
ARC-AGI
93.7%自報
Graphwalks BFS <128k
93.0%自報
Graphwalks parents <128k
89.8%自報
ARC-AGI v2
73.3%自報
AA 評測指數
Intelligence Index39.1
Gpqa0.9
Tau20.7
Lcr0.7
Ifbench0.7
Scicode0.5
Terminalbench Hard0.4
Hle0.3
LLM Stats 分類評分
Finance100
Legal100
General100
Agents100
Reasoning63
Communication100
Physics90
Structured Output90
Biology90
Chemistry90
Multimodal80
Search80
Vision80
Spatial Reasoning70
Tool Calling70
Math60
Code60
Long Context40
Healthcare30
定價
輸入價格$2.625 / 1M tokens
輸出價格$15.75 / 1M tokens
混合價格(3:1)$5.906 / 1M tokens
快取讀取價格$0.25 / 1M tokens
速度
Tokens/秒133.1
首Token延遲1.11s
首回答延遲1.11s
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
$0
$0.00002
比較該模型在不同 API 供應商之間的定價。