llmboard.aiAI model intelligence
Home

Model Rankings

OverallOpen ModelsAgentCodingReasoningMathKnowledgeInstruction FollowingTextVision
Image GenerationImage Editing
Video GenerationImage to VideoVideo Editing
Text to SpeechSpeech to Text
Embeddings

Efficiency

Chat Token PricingImage PricingVideo PricingAudio Pricing
Chat Speed & LatencyProvider Reliability

Benchmarks

GPQAMMLU-ProAIME 2025SWE-Bench VerifiedMMLUHumanity's Last ExamLiveCodeBenchMATHHumanEvalMMMU-Pro
All Benchmarks

Tools

Model DirectoryCompare Models

Scoring & Data

Scoring & Data
393 models668 benchmarks

Leaderboard Center

Overall RankingCodingCore BenchmarksPrice & ValueRuntime Performance

Modalities

All ModelsImage GenerationImage EditingVideo GenerationImage-to-VideoVideo EditingText-to-SpeechSpeech-to-TextEmbeddings

Data & Methods

Scoring MethodAll BenchmarksReasoningMath

Vendors

All VendorsOpenAIAnthropicGoogle
llmboard.aiCopyright 2026 llmboard.ai

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 17, 2026. Default version: o3-mini

Compare
LLMBoard Score35.2o3-mini
Coverage100%25 benchmark families
Context window200KTokens
Official input price$1.1OpenAI API

On this page

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

o3 mini Capability Profile

This profile uses the model's current scored version. Arena ratings and prices are shown separately.

o3-mini LLMBoard score breakdown

o3 mini Benchmark Results

Benchmark scores for o3-mini.

25 rows
Columns

Show columns

Sort by
Benchmark
Score
Rank
Participants
Percentile
Evidence
Evaluated
BenchmarkLiveBenchScore84.6%Rank01Participants38Percentile100.0%EvidenceCEvaluatedAug 17, 2026
BenchmarkMATHScore97.9%Rank01Participants71Percentile100.0%EvidenceCEvaluatedAug 17, 2026
BenchmarkMultilingual MMLUScore80.7%Rank01Participants5Percentile100.0%EvidenceCEvaluatedAug 17, 2026
BenchmarkCOLLIEScore98.7%Rank02Participants10Percentile88.9%EvidenceCEvaluatedAug 17, 2026
BenchmarkMGSMScore92.0%Rank02Participants31Percentile96.7%EvidenceCEvaluatedAug 17, 2026
BenchmarkAider-Polyglot EditScore60.4%Rank03Participants10Percentile77.8%EvidenceCEvaluatedAug 17, 2026
BenchmarkInternal API instruction following (hard)Score50.0%Rank03Participants7Percentile66.7%EvidenceCEvaluatedAug 17, 2026
BenchmarkMulti-IFScore79.5%Rank03Participants23Percentile90.9%EvidenceCEvaluatedAug 17, 2026
BenchmarkSWE-LancerScore18.0%Rank04Participants4Percentile0.0%EvidenceCEvaluatedAug 17, 2026
BenchmarkIFEvalScore93.9%Rank05Participants67Percentile93.9%EvidenceCEvaluatedAug 17, 2026
BenchmarkComplexFuncBenchScore17.6%Rank06Participants7Percentile16.7%EvidenceCEvaluatedAug 17, 2026
BenchmarkSWE-Lancer (IC-Diamond subset)Score7.4%Rank06Participants6Percentile0.0%EvidenceCEvaluatedAug 17, 2026
BenchmarkGraphwalks parents <128kScore58.3%Rank07Participants11Percentile40.0%EvidenceCEvaluatedAug 17, 2026
BenchmarkAider-PolyglotScore66.7%Rank09Participants22Percentile61.9%EvidenceCEvaluatedAug 17, 2026
BenchmarkGraphwalks BFS <128kScore51.0%Rank09Participants11Percentile20.0%EvidenceCEvaluatedAug 17, 2026
BenchmarkOpenAI-MRCR: 2 needle 128kScore18.7%Rank09Participants9Percentile0.0%EvidenceCEvaluatedAug 17, 2026
BenchmarkAIME 2024Score87.3%Rank12Participants53Percentile78.8%EvidenceCEvaluatedAug 17, 2026
BenchmarkFrontierMathScore9.2%Rank15Participants17Percentile12.5%EvidenceCEvaluatedAug 17, 2026
BenchmarkTAU-bench AirlineScore32.4%Rank21Participants23Percentile9.1%EvidenceCEvaluatedAug 17, 2026
BenchmarkTAU-bench RetailScore57.6%Rank21Participants25Percentile16.7%EvidenceCEvaluatedAug 17, 2026
BenchmarkMulti-ChallengeScore39.9%Rank23Participants29Percentile21.4%EvidenceCEvaluatedAug 17, 2026
BenchmarkMMLUScore86.9%Rank27Participants101Percentile74.0%EvidenceCEvaluatedAug 17, 2026
BenchmarkSimpleQAScore15.0%Rank38Participants47Percentile19.6%EvidenceCEvaluatedAug 17, 2026
BenchmarkSWE-Bench VerifiedScore49.3%Rank95Participants111Percentile14.6%EvidenceCEvaluatedAug 17, 2026
BenchmarkGPQAScore77.2%Rank102Participants239Percentile57.6%EvidenceCEvaluatedAug 17, 2026

o3 mini Arena Results

Preference and agent-evaluation results for the default version.

4 rows
Columns

Show columns

Sort by
Arena
Category
Rank
Rating / score
Votes
Observations
Result date
Arenatext style controlCategoryoverallRank179Rating / score1363.5Votes18,589ObservationsN/AResult dateAug 12, 2026
ArenatextCategoryoverallRank194Rating / score1336.6Votes18,589ObservationsN/AResult dateAug 12, 2026
Arenatext style controlCategoryoverallRank197Rating / score1347.9Votes57,455ObservationsN/AResult dateAug 12, 2026
ArenatextCategoryoverallRank210Rating / score1319.3Votes57,455ObservationsN/AResult dateAug 12, 2026

o3 mini Pricing

Official vendor API pricing appears first, followed by individual provider offers.

Official API
$1.1 input, $4.4 output per 1M
Official provider
OpenAI
Lowest third-party
From $0.99 input, $4 output per 1M via Poe
Tracked offerings
18
17 rows
Columns

Show columns

Sort by
Provider
Provider model ID
Region
Input / 1M
Output / 1M
Context
Updated
ProviderPoeProvider model IDopenai/o3-miniRegionglobalInput / 1M$0.99Output / 1M$4Context200KUpdatedAug 17, 2026
ProviderNanoGPTProvider model IDopenai/o3-miniRegionglobalInput / 1M$1.1Output / 1M$4.4Context200KUpdatedAug 17, 2026
ProviderImpossiblProvider model IDopenai/o3-miniRegionglobalInput / 1M$1.1Output / 1M$4.4Context200KUpdatedAug 17, 2026
ProviderJiekou.AIProvider model IDo3-miniRegionglobalInput / 1M$1.1Output / 1M$4.4Context131.1KUpdatedAug 17, 2026
ProviderOpenRouterProvider model IDopenai/o3-miniRegionglobalInput / 1M$1.1Output / 1M$4.4Context200KUpdatedAug 17, 2026
ProviderOpenAIProvider model IDo3-miniRegionglobalInput / 1M$1.1Output / 1M$4.4Context200KUpdatedAug 17, 2026
ProviderNEAR AI CloudProvider model IDopenai/o3-miniRegionglobalInput / 1M$1.1Output / 1M$4.4Context200KUpdatedAug 17, 2026
ProviderMerge GatewayProvider model IDopenai/o3-miniRegionglobalInput / 1M$1.1Output / 1M$4.4Context200KUpdatedAug 17, 2026
ProviderCloudflare AI GatewayProvider model IDopenai/o3-miniRegionglobalInput / 1M$1.1Output / 1M$4.4Context200KUpdatedAug 17, 2026
ProviderHeliconeProvider model IDo3-miniRegionglobalInput / 1M$1.1Output / 1M$4.4Context200KUpdatedAug 17, 2026
ProviderAzure Cognitive ServicesProvider model IDo3-miniRegionglobalInput / 1M$1.1Output / 1M$4.4Context200KUpdatedAug 17, 2026
ProviderAzureProvider model IDo3-miniRegionglobalInput / 1M$1.1Output / 1M$4.4Context200KUpdatedAug 17, 2026
ProviderVercel AI GatewayProvider model IDopenai/o3-miniRegionglobalInput / 1M$1.1Output / 1M$4.4Context200KUpdatedAug 17, 2026
ProviderEden AIProvider model IDopenai/o3-miniRegionglobalInput / 1M$1.1Output / 1M$4.4Context200KUpdatedAug 17, 2026
ProviderLLM GatewayProvider model IDo3-miniRegionglobalInput / 1M$1.1Output / 1M$4.4Context200KUpdatedAug 17, 2026
ProviderKilo GatewayProvider model IDopenai/o3-miniRegionglobalInput / 1M$1.1Output / 1M$4.4Context200KUpdatedAug 17, 2026
ProviderAbacusProvider model IDo3-miniRegionglobalInput / 1M$1.1Output / 1M$4.4Context200KUpdatedAug 17, 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 Runtime Performance

Provider-specific output speed and catalog latency for o3-mini. Runtime does not affect the capability score.

2 rows
Columns

Show columns

Sort by
Provider
Output Speed
Catalog Latency
Max Input
Max Output
Updated
ProviderAzureOutput Speed115 tok/sCatalog Latency5.2 sMax Input200KMax Output100KUpdatedAug 17, 2026
ProviderOpenAIOutput Speed115 tok/sCatalog Latency5.2 sMax Input200KMax Output100KUpdatedAug 17, 2026

Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.

o3 mini Specifications

Technical details for the model's 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

o3 mini Versions

Available versions of this model. The score column identifies the version used in the overall ranking.

1 rows
Columns

Show columns

Sort by
Version
Released
LLMBoard
Parameters
Context
Max output
Open weights
License
Versiono3-miniReleasedJan 30, 2025LLMBoard35.2ParametersN/AContext200KMax output100KOpen weightsNoLicenseProprietary

o3 mini vs nearby models

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

o3 minivsQwen3 Next 80B A3Bo3 minivsGPT-4.5o3 minivsGrok Code Fast 1o3 minivsQwen3 Coder 480B A35Bo3 minivsNemotron 3 Nanoo3 minivsMiniMax M1 40K

Models similar to o3 mini

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

#152+0.5
OP

GPT-4.5

OpenAI

35.7 LLMBoard

DetailsCompare
#150+0.7
OP

o1

OpenAI

35.9 LLMBoard

DetailsCompare
#159-1.6
OP

o1 pro

OpenAI

33.6 LLMBoard

DetailsCompare
#168-3.9
OP

GPT-4.1

OpenAI

31.3 LLMBoard

DetailsCompare
#137+4.5
OP

GPT-5.3

OpenAI

39.7 LLMBoard

DetailsCompare
#171-4.8
OP

GPT-5-nano

OpenAI

30.3 LLMBoard

DetailsCompare

What is o3 mini?

Key information about o3 mini and its available data.

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.

Data as of 2026-08-17.

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 $0.99 input and $4 output via Poe.

Who created o3 mini?

o3 mini was created by OpenAI.

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?

18 provider offerings are linked to the default version.

What models should I compare o3 mini with?

Nearby ranked alternatives include Qwen3 Next 80B A3B, GPT-4.5, Grok Code Fast 1.