跳轉到主要內容
AITier

o3-mini

OpenAIOpenAI o-seriesProprietary

描述

A smaller variant of O3, expected to offer enhanced multimodal capabilities, improved reasoning, and more efficient resource utilization compared to previous models while maintaining strong performance on core tasks.

發布日期
2025-01-31
參數規模
—
上下文長度
200K
支援模態
text

能力雷達圖

35
general
65
coding
83
reasoning
49
science
40
agents
0
multimodal

排行榜排名

領域#排名分數來源
程式碼能力榜270
44.0
AA
通用能力榜296
44.0
AA
科學能力228
52.0
AA

基準測試分數 (LLM Stats)

(LLM Stats (zeroeval))

Biology

GPQANYU + Cohere + Anthropic (2023)77.2%自報

Code

Aider-Polyglot66.7%自報
Aider-Polyglot Edit60.4%自報
SWE-Bench Verified49.3%自報
SWE-Lancer18.0%自報
SWE-Lancer (IC-Diamond subset)7.4%自報

Communication

Multi-IF79.5%自報
TAU-bench Retail57.6%自報
Multi-Challenge39.9%自報
TAU-bench Airline32.4%自報

Factuality

SimpleQA15.0%自報

Finance

MMLU86.9%自報

General

IFEvalGoogle Research (2023)93.9%自報
LiveBench84.6%自報
Multilingual MMLU80.7%自報
Internal API instruction following (hard)50.0%自報

Language

COLLIE98.7%自報

Long Context

OpenAI-MRCR: 2 needle 128k18.7%自報
ComplexFuncBench17.6%自報

Math

MATH97.9%自報
MGSM92.0%自報
AIME 202487.3%自報
FrontierMath9.2%自報

Reasoning

Graphwalks parents <128k58.3%自報
Graphwalks BFS <128k51.0%自報

AA 評測指數

(Artificial Analysis)
Intelligence Index(Artificial Analysis)
19.2
Math 500(OpenAI (2024), subset of Hendrycks et al. MATH (2021))
1.0
Mmlu Pro(TIGER-Lab (Univ. of Waterloo, Toronto, CMU, 2024))
0.8
Aime(MAA (Mathematical Association of America))
0.8
Gpqa(NYU + Cohere + Anthropic (2023))
0.7
Livecodebench(UC Berkeley + MIT + Cornell (2024))
0.7
Scicode(UIUC + Argonne National Lab (2024))
0.4
Tau2(Sierra + U Toronto + Vector Institute (2025))
0.3
Hle(Center for AI Safety + Scale AI (2025))
0.1
Terminalbench Hard(Stanford × Laude Institute (2026))
0.1

LLM Stats 分類評分

(LLM Stats (zeroeval))
Writing
100
Legal
90
Instruction Following
90
Language
90
Finance
90
Healthcare
90
Math
80
Physics
80
Biology
80
Chemistry
80
Reasoning
60
Structured Output
60
General
60
Spatial Reasoning
50
Frontend Development
50
Communication
50
Code
40
Tool Calling
40
Long Context
20
Factuality
10

定價

輸入價格$1.1 / 1M tokens
輸出價格$4.4 / 1M tokens
混合價格(3:1)$1.925 / 1M tokens
快取讀取價格$0.55 / 1M tokens

速度

Tokens/秒0.0
首Token延遲0.00s
首回答延遲0.00s

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
$1.1
$4.4

比較該模型在不同 API 供應商之間的定價。

外部連結

LLM StatsArtificial Analysis