GPT-5.4 nano (medium)
OpenAIGPTProprietary
描述
GPT-5.4 nano is OpenAI's cheapest GPT-5.4-class model for simple high-volume tasks. It is optimized for classification, data extraction, ranking, and lightweight coding subagents, while preserving strong reasoning, multimodal understanding, and tool use for latency-sensitive workloads.
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
19
general
50
coding
76
reasoning
58
science
60
agents
85
multimodal
排行榜排名
基准测试分数 (LLM Stats)
(LLM Stats (zeroeval))Agents
Finance Agent v2
38.2%
Toolathlon
35.5%自报
Communication
Tau2 Telecom
92.5%自报
Long Context
MRCR v2 (8-needle)
33.1%自报
Math
LiveBench
70.1%
Multimodal
OSWorld-Verified
39.0%自报
Reasoning
GPQANYU + Cohere + Anthropic (2023)
82.8%自报
Graphwalks BFS <128k
73.4%自报
MCP Atlas
56.1%自报
SWE-Bench ProPrinceton NLP (2024)
52.4%自报
Graphwalks parents <128k
50.8%自报
Terminal-Bench 2.0Stanford × Laude Institute (2026)
46.3%自报
Humanity's Last Exam
24.3%自报
Vision
OmniDocBench 1.5
75.8%自报
MMMU-Pro
66.1%自报
AA 评测指数
(Artificial Analysis)Gpqa(NYU + Cohere + Anthropic (2023))76.1
Lcr(Artificial Analysis)67.3
Ifbench(Google Research (2023))64.4
Tau2(Sierra + U Toronto + Vector Institute (2025))52.6
Terminalbench Hard(Stanford × Laude Institute (2026))33.3
Intelligence Index(Artificial Analysis)20.0
Hle(Center for AI Safety + Scale AI (2025))15.9
LLM Stats 分类评分
(LLM Stats (zeroeval))Spatial Reasoning9
Vision6
Reasoning3
General2
Communication90
Physics80
Structured Output80
Biology80
Chemistry80
Multimodal70
Tool Calling60
Long Context50
Math50
Code50
Finance40
Agents40
Healthcare30
定价
输入价格$0.2 / 1M tokens
输出价格$1.25 / 1M tokens
混合价格(3:1)$0.463 / 1M tokens
缓存读取价格$0.02 / 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。