GPT-5.4 mini (Non-Reasoning)
OpenAIGPTProprietary
描述
GPT-5.4 mini is OpenAI's strongest mini model yet for coding, computer use, and subagents. It brings many of the strengths of GPT-5.4 to a faster, more efficient model designed for high-volume workloads, with strong coding, reasoning, multimodal understanding, and tool use.
发布日期
2026-03-17
参数规模
—
上下文长度
400K
支持模态
image, text
能力雷达图
14
general
40
coding
61
reasoning
42
science
60
agents
85
multimodal
排行榜排名
基准测试分数 (LLM Stats)
(LLM Stats (zeroeval))Agents
OSWorld-Verified
72.1%自报
Terminal-Bench 2.0Stanford × Laude Institute (2026)
60.0%自报
MCP Atlas
57.7%自报
SWE-Bench ProPrinceton NLP (2024)
54.4%自报
Finance Agent v2
45.4%
Toolathlon
42.9%自报
Legal Agent Benchmark
0.0%
Biology
GPQANYU + Cohere + Anthropic (2023)
88.0%自报
Communication
Tau2 Telecom
93.4%自报
General
MMMU-Pro
76.6%自报
MRCR v2 (8-needle)
33.6%自报
Math
Humanity's Last Exam
28.2%自报
Multimodal
OmniDocBench 1.5
87.4%自报
Reasoning
Graphwalks BFS <128k
76.3%自报
Graphwalks parents <128k
71.5%自报
AA 评测指数
(Artificial Analysis)Intelligence Index(Artificial Analysis)16.8
Gpqa(NYU + Cohere + Anthropic (2023))0.6
Scicode(UIUC + Argonne National Lab (2024))0.4
Ifbench(Google Research (2023))0.4
Lcr(Artificial Analysis)0.3
Tau2(Sierra + U Toronto + Vector Institute (2025))0.2
Terminalbench Hard(Stanford × Laude Institute (2026))0.2
Hle(Center for AI Safety + Scale AI (2025))0.1
LLM Stats 分类评分
(LLM Stats (zeroeval))Physics90
Structured Output90
Biology90
Chemistry90
Communication90
Multimodal80
Spatial Reasoning70
Vision70
Code60
Tool Calling60
Reasoning50
Finance50
General50
Agents50
Math30
Long Context20
Healthcare20
Legal0
定价
输入价格$0.75 / 1M tokens
输出价格$4.5 / 1M tokens
混合价格(3:1)$1.688 / 1M tokens
缓存读取价格$0.075 / 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
供应商价格排行
1 个供应商
供应商输入输出
1OpenAI
$0
$0
比较该模型在不同 API 供应商之间的定价。