跳转到主要内容

o4-mini (high)

OpenAIOpenAI o-seriesProprietary

描述

o4-mini is OpenAI's latest small o-series model, optimized for fast, effective reasoning with exceptionally efficient performance in coding and visual tasks. It is faster and more affordable than o3.

发布日期
2025-04-16
参数规模
上下文长度
200K
支持模态
image, text

能力雷达图

42
general
77
coding
92
reasoning
55
science
60
agents
85
multimodal

排行榜排名

领域#排名分数来源
智能体能力模型榜82
44.0
LS
代码能力榜153
63.0
AA
通用能力榜158
61.0
AA
多模态榜53
45.0
LS
科学能力154
62.0
AA

基准测试分数 (LLM Stats)

(LLM Stats (zeroeval))

Agents

BrowseCompOpenAI (2025)51.5%自报

Biology

GPQANYU + Cohere + Anthropic (2023)81.4%自报

Code

Aider-Polyglot68.9%自报
SWE-Bench Verified68.1%自报
Aider-Polyglot Edit58.2%自报

Communication

TAU-bench Retail71.8%自报
TAU-bench Airline49.2%自报
Multi-Challenge43.0%自报

General

MMMU81.6%自报

Math

AIME 202493.4%自报
AIME 202592.7%自报
MathVista84.3%自报
Humanity's Last Exam14.7%自报

Multimodal

CharXiv-R72.0%自报

AA 评测指数

(Artificial Analysis)
Math Index(Artificial Analysis)
90.7
Intelligence Index(Artificial Analysis)
26.1
Math 500(OpenAI (2024), subset of Hendrycks et al. MATH (2021))
1.0
Aime(MAA (Mathematical Association of America))
0.9
Aime 25(MAA (Mathematical Association of America))
0.9
Livecodebench(UC Berkeley + MIT + Cornell (2024))
0.9
Mmlu Pro(TIGER-Lab (Univ. of Waterloo, Toronto, CMU, 2024))
0.8
Gpqa(NYU + Cohere + Anthropic (2023))
0.8
Ifbench(Google Research (2023))
0.7
Lcr(Artificial Analysis)
0.6
Tau2(Sierra + U Toronto + Vector Institute (2025))
0.6
Scicode(UIUC + Argonne National Lab (2024))
0.5
Hle(Center for AI Safety + Scale AI (2025))
0.2
Terminalbench Hard(Stanford × Laude Institute (2026))
0.2

LLM Stats 分类评分

(LLM Stats (zeroeval))
Multimodal
80
Physics
80
Healthcare
80
Biology
80
Chemistry
80
Math
70
Reasoning
70
Frontend Development
70
General
70
Code
70
Tool Calling
60
Vision
60
Search
50
Agents
50
Communication
50

定价

输入价格$1.1 / 1M tokens
输出价格$4.4 / 1M tokens
混合价格(3:1)$1.925 / 1M tokens
缓存读取价格$0.275 / 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

16 个供应商

最便宜: Poe最贵: Impossibl
供应商输入输出
1Poe最便宜
$0.99
$4
2OpenAI主要
$1.1
$4.4
3NanoGPT
$1.1
$4.4
4Abacus
$1.1
$4.4
5OpenRouter
$1.1
$4.4
6Jiekou.AI
$1.1
$4.4
7Kilo Gateway
$1.1
$4.4
8Cloudflare AI Gateway
$1.1
$4.4
9Helicone
$1.1
$4.4
10Azure Cognitive Services
$1.1
$4.4
11Vercel AI Gateway
$1.1
$4.4
12LLM Gateway
$1.1
$4.4
13Azure
$1.1
$4.4
14NEAR AI Cloud
$1.1
$4.4
15Merge Gateway
$1.1
$4.4
16Impossibl
$1.1
$4.4

比较该模型在不同 API 供应商之间的定价。

外部链接