llmboard.ai
Benchmarks
CompareRankings
llmboard.ai
Benchmarks
CompareRankings
HomeModelso3 mini

OpenAI model product

o3 mini

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.

Updated Aug 10, 2026. Default version: o3-mini

Compare
LLMBoard score61.6o3-mini
Coverage80%15 benchmark families
Context window200KTokens
Official input price$1.1OpenAI API

On this page

  • Specification
  • Capability
  • Benchmarks
  • Arena
  • Pricing
  • Versions
  • About
  • Compare
  • Similar models
  • FAQ

Model specification

Structured fields from the published default version.

Version
o3-mini
Released
Jan 30, 2025
Knowledge cutoff
Sep 30, 2023
Parameters
N/A
Context window
200K
Max output
100K
Inputs
text
Outputs
text
Open weights
No
License
Proprietary

Capability profile

This profile uses the latest version under this unique model that has a calculated LLMBoard score. Arena and price are excluded.

o3-mini category scores

Benchmark results

Published benchmark records for the scored version o3-mini.

25 rows
Columns

Show columns

LiveBench0.8138100.0%CAug 7, 2026
MATH1.0171100.0%CAug 7, 2026
Multilingual MMLU0.815100.0%CAug 7, 2026
COLLIE1.021088.9%CAug 7, 2026
MGSM0.923196.7%CAug 7, 2026
Multi-IF0.822094.7%CAug 7, 2026
Aider-Polyglot Edit0.631077.8%CAug 7, 2026
Internal API instruction following (hard)0.53766.7%CAug 7, 2026
SWE-Lancer0.2440.0%CAug 7, 2026
IFEval0.956593.8%CAug 7, 2026
ComplexFuncBench0.26716.7%CAug 7, 2026
SWE-Lancer (IC-Diamond subset)0.1660.0%CAug 7, 2026
Aider-Polyglot0.792261.9%CAug 7, 2026
OpenAI-MRCR: 2 needle 128k0.2990.0%CAug 7, 2026
Graphwalks parents <128k0.6101847.1%CAug 7, 2026
AIME 20240.9125378.8%CAug 7, 2026
FrontierMath0.1151712.5%CAug 7, 2026
Graphwalks BFS <128k0.5152233.3%CAug 7, 2026
TAU-bench Airline0.321239.1%CAug 7, 2026
TAU-bench Retail0.6212516.7%CAug 7, 2026
Multi-Challenge0.4232921.4%CAug 7, 2026
MMLU0.92710073.7%CAug 7, 2026
SimpleQA0.1374620.0%CAug 7, 2026
SWE-Bench Verified0.58810415.5%CAug 7, 2026
GPQA0.89723358.6%CAug 7, 2026

Arena results

Preference and agent-evaluation signals from published Arena datasets.

58 rows
Columns

Show columns

text style controljapanese1441299.31,323N/AAug 6, 2026
text style controlindustry mathematical1501391.24,379N/AAug 6, 2026
textjapanese1511266.41,323N/AAug 6, 2026
textindustry mathematical1541378.44,379N/AAug 6, 2026
text style controlmath1591381.54,715N/AAug 6, 2026
text style controlkorean1621292.91,070N/AAug 6, 2026
textmath1631373.44,715N/AAug 6, 2026
textkorean1691262.21,070N/AAug 6, 2026
text style controlcoding1711416.09,450N/AAug 6, 2026
text style controlgerman1721327.11,281N/AAug 6, 2026
textgerman1751302.91,281N/AAug 6, 2026
text style controlfrench1761355.9656N/AAug 6, 2026
text style controlpolish1761324.32,576N/AAug 6, 2026
textfrench1771318.6656N/AAug 6, 2026
text style controlexpert1781365.22,860N/AAug 6, 2026
textpolish1791291.32,576N/AAug 6, 2026
textexpert1821330.22,860N/AAug 6, 2026
textspanish1841299.9836N/AAug 6, 2026
text style controlhard prompts1851370.420,096N/AAug 6, 2026
text style controlindustry software and it services1851389.616,857N/AAug 6, 2026
text style controlspanish1851327.5836N/AAug 6, 2026
textcoding1861362.49,450N/AAug 6, 2026
text style controlhard prompts english1871383.411,279N/AAug 6, 2026
text style controlinstruction following1871343.416,948N/AAug 6, 2026
text style controllonger query1871358.59,217N/AAug 6, 2026
textinstruction following1901315.216,948N/AAug 6, 2026
textlonger query1911327.19,217N/AAug 6, 2026
text style controloverall1931347.857,283N/AAug 6, 2026
text style controlnon english1931326.426,897N/AAug 6, 2026
text style controlexclude ties1951306.940,039N/AAug 6, 2026
texthard prompts english1961344.611,279N/AAug 6, 2026
texthard prompts1971332.620,096N/AAug 6, 2026
text style controlindustry writing and literature and language1971324.113,426N/AAug 6, 2026
text style controlenglish1981363.130,380N/AAug 6, 2026
text style controlmulti turn1981339.79,489N/AAug 6, 2026
text style controlchinese1991360.33,363N/AAug 6, 2026
textchinese2001323.53,363N/AAug 6, 2026
textindustry software and it services2001343.816,857N/AAug 6, 2026
textrussian2011298.64,436N/AAug 6, 2026
text style controlrussian2021326.64,436N/AAug 6, 2026
textnon english2031298.326,897N/AAug 6, 2026
textexclude ties2061265.540,039N/AAug 6, 2026
textoverall2071319.257,283N/AAug 6, 2026
textmulti turn2071313.19,489N/AAug 6, 2026
text style controlindustry entertainment and sports and media2081301.510,284N/AAug 6, 2026
textenglish2091334.030,380N/AAug 6, 2026
textindustry writing and literature and language2091294.213,426N/AAug 6, 2026
text style controlindustry business and management and financial operations2101326.67,707N/AAug 6, 2026
textindustry entertainment and sports and media2111272.910,284N/AAug 6, 2026
text style controlindustry life and physical and social science2111350.09,650N/AAug 6, 2026
textindustry legal and government2121305.43,632N/AAug 6, 2026
textindustry business and management and financial operations2131288.27,707N/AAug 6, 2026
textindustry medicine and healthcare2131298.63,043N/AAug 6, 2026
text style controlcreative writing2131301.08,178N/AAug 6, 2026
textindustry life and physical and social science2141315.59,650N/AAug 6, 2026
text style controlindustry medicine and healthcare2141342.53,043N/AAug 6, 2026
text style controlindustry legal and government2151340.03,632N/AAug 6, 2026
textcreative writing2161273.08,178N/AAug 6, 2026

Pricing

Official vendor API PAYG pricing is summarized first. The table then lists individual provider offerings without treating their minimum as the official price.

Official API
$1.1 input, $4.4 output per 1M
Official provider
OpenAI
Lowest third-party
From $1.1 input, $4.4 output per 1M via LLM Gateway
Tracked offerings
7
7 rows
Columns

Show columns

LLM Gatewayo3-miniglobal$1.1$4.4200KAug 7, 2026
Heliconeo3-miniglobal$1.1$4.4200KAug 7, 2026
Abacuso3-miniglobal$1.1$4.4200KAug 7, 2026
Azure Cognitive Serviceso3-miniglobal$1.1$4.4200KAug 7, 2026
Azureo3-miniglobal$1.1$4.4200KAug 7, 2026
Jiekou.AIo3-miniglobal$1.1$4.4131.1KAug 7, 2026
OpenAIo3-miniglobal$1.1$4.4200KAug 7, 2026

Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.

o3 mini versions

All published versions linked to this unique model. The score columns identify the version used by the current overall ranking.

1 rows
Columns

Show columns

o3-miniJan 30, 202561.6N/A200K100KNoProprietary

What is o3 mini?

A concise description based on the published model registry.

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.

Use the benchmark, Arena and pricing sections above as separate evidence. A missing field means the current data snapshot does not support that claim.

Data snapshot: 2026-08-07. Editorial model content is not available in the backend.

o3 mini vs nearby models

Open a comparison with the three ranked models immediately above and below this model.

o3 minivsLlama 3.3 Nemotron Super 49Bo3 minivsLlama 3.1 Nemotron Ultra 253Bo3 minivsGLM 4.5o3 minivsQwen3.5 122B A10Bo3 minivsLongCat Flash Thinkingo3 minivsNemotron Nano 9B

Models similar to o3 mini

Recommendations prioritize the same model type and family, then the closest published LLMBoard score.

#45+1.4
OP

o1

OpenAI

63.0 LLMBoard

DetailsCompare
#56-2.8
OP

GPT-4.5

OpenAI

58.8 LLMBoard

DetailsCompare
#60-4.6
OP

GPT-OSS-120B

OpenAI

56.9 LLMBoard

DetailsCompare
#61-5.0
OP

GPT-5.4-mini

OpenAI

56.5 LLMBoard

DetailsCompare
#64-5.8
OP

o3

OpenAI

55.8 LLMBoard

DetailsCompare
#67-6.6
OP

o4 mini

OpenAI

55.0 LLMBoard

DetailsCompare

FAQ

Common questions about o3 mini.

When was o3 mini released?

o3 mini's default version was released on Jan 30, 2025.

How much does o3 mini cost?

o3 mini's official API price is $1.1 per million input tokens and $4.4 per million output tokens via OpenAI. The lowest tracked third-party offer starts at $1.1 input and $4.4 output via LLM Gateway.

Who created o3 mini?

o3 mini is published under OpenAI in the model registry.

What is the context window for o3 mini?

The default version has a 200K token context window.

Is o3 mini open weight?

No. The default version is not marked as having publicly available weights.

How many API providers offer o3 mini?

7 published provider offerings are linked to the default version.

What models should I compare o3 mini with?

Nearby ranked alternatives include Llama 3.3 Nemotron Super 49B, Llama 3.1 Nemotron Ultra 253B, GLM 4.5.

Rankings

OverallCodingText ArenaPricing

Modalities

Image GenerationVideo GenerationSpeech-to-TextEmbeddings

Benchmarks

All BenchmarksReasoningMathCoding

Vendors

All VendorsOpenAIAnthropicGoogle
llmboard.aiCopyright 2026 llmboard.ai