Skip to content

OpenAI · Chat

o3 Mini

OpenAI 🇺🇸ChatOpenAI familyOne of its sources says the weights aren't publicly available.The maker lists this model as deprecated (23 Oct 2026).

Newer version: o4 Mini. We compared release dates and version names in our catalogue.

From Eurouter's listing:
o3-mini is OpenAI's compact text-only reasoning model optimized for cost-efficient coding, math, science, and structured-output tasks.
llminfo IQ
122.8
Max context
200K
Listings
42

Evidence and sources

llminfo IQ 122.8, ranked among chat models. From 317 benchmarks. Plenty of data behind it.How llminfo IQ is computedCoding IQ 95.3, 95% interval 88–102. From 12 benchmark families across 10 sources. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.How Coding IQ is computedPoor value (37.8). Costs more per task than its benchmark results predict. From 18 benchmarks with measured task costs. Plenty of data behind it.How Value for money worksReleased 31 Jan 2025 Training-data cutoff, as its sources state it Maker HQ: US (according to OpenAI's own website)
All rankings: #37 in Hacker News discussions this week #519 on OpenRouter this monthAll rankings: #37 in Hacker News discussions this week #519 on OpenRouter this monthSources: LMArena data, Models.dev data, LiteLLM data, OpenRouter data docs, EURouter data, llminfo researchPrimary data from LMArena from Models.dev: name, weights availability from LiteLLM: deprecation date from OpenRouter: knowledge cutoff from EURouter: description from llminfo research: release date
Tags from its sources:reasoninglong-contextefficientcodingmath

Advantages and trade-offs

Compared with 10 chat models, picked mainly by popularity and IQ

Trade-offs

Deprecated by its maker

The maker has already deprecated this model (23 Oct 2026).

No open weights

The weights aren't public, so you can't run it yourself.

We only make a claim when there's enough data on models of the same type. Updated 22 Nov, 04:34 UTC.

Input & output

as stated by the model's providers
Text
Images
Files
Text

Capabilities

Supported operations and provider-stated features

VisionReasoningFunction callingStructured outputPrompt cachingBatch API

Listings

 OpenAIo3-mini-batch · batchSource: Helicone Costs dataNot published by the provider$0.55$2.20—
 Microsoft Azureo3-mini-batch · batchSource: Helicone Costs dataNot published by the provider$0.55$2.20—
 OpenRouteropenai/o3-mini:batch · batchSource: OpenRouter data docs200K$0.55cache read $0.275$2.20—
 Poeopenai/o3-miniSource: Models.dev data200K$0.99$4.00—
 Jiekouo3-miniSource: Models.dev data200K$1.045cache read $0.5225$4.18—
 302aio3-miniSource: 302.ai data128K$1.10$4.40—
 Aihubmixo3-miniSource: AIHubMix data docs200K$1.10cache read $0.55$4.40—
 Fastrouteropenai/o3-miniSource: FastRouter data200K$1.10cache read $0.55batch $0.55$4.40batch $2.20—
 Flowdotopenai/o3-miniSource: FlowDot data200K$1.10$4.40—
 Kiloopenai/o3-miniSources: Kilo AI Gateway data, Models.dev data200K$1.10cache read $0.55$4.40$0.00
Show all 35 listings

Showing 10 of 35: the maker's own listing first, then the cheapest per 1M input tokens from each provider.

Also sold by Abacus, Cloudflare AI Gateway, Core42, Digitalocean, Eurouter, Gradient AI, Impossibl, Merge Gateway, Vercel, Vercel AI Gateway.

7 listings without a price are hidden.

Benchmarks

Named effort levels run from lowest to highest. Select a result to see its source details.

Coding

Source: JudgeBench data docs
GPT-4o Dataset, Prompted Judge, Arena-Hard (o3-mini-2025-01-31 (high)), Coding Score
GPT-4o Dataset, Prompted Judge, Arena-Hard (o3-mini-2025-01-31 (low)), Coding Score
GPT-4o Dataset, Prompted Judge, Arena-Hard (o3-mini-2025-01-31 (medium)), Coding Score
LiveCodeBench8 related benchmarks · 22 results
LiveCodeBench
Source: LiveCodeBench Leaderboard data
AtCoder
Source: LiveCodeBench Leaderboard data
platform:atcoder, high
platform:atcoder, low
platform:atcoder, Med
Codeforces
Source: LiveCodeBench Leaderboard data
platform:codeforces, high
platform:codeforces, low
platform:codeforces, Med
Easy
Source: LiveCodeBench Leaderboard data
difficulty:easy, high
difficulty:easy, low
difficulty:easy, Med
Hard
Source: LiveCodeBench Leaderboard data
difficulty:hard, high
difficulty:hard, low
difficulty:hard, Med
LeetCode
Source: LiveCodeBench Leaderboard data
platform:leetcode, high
platform:leetcode, low
platform:leetcode, Med
Show 4 more resultsHide 4 results
Medium
Source: LiveCodeBench Leaderboard data
difficulty:medium, high
difficulty:medium, low
difficulty:medium, Med
Pro
Source: LiveCodeBench Pro data · Sep 2025
Multi-SWE-bench9 related benchmarks · 27 results
C Verified
Source: Multi-SWE-bench Experiments data docs · Mar 2025
MagentLess, 20250329_MagentLess_OpenAI-o3-mini-high
MopenHands, 20250329_MopenHands_OpenAI-o3-mini-high
MSWE-agent, 20250329_MSWE-agent_OpenAI-o3-mini-high
C++ Verified
Source: Multi-SWE-bench Experiments data docs · Mar 2025
MagentLess, 20250329_MagentLess_OpenAI-o3-mini-high
MopenHands, 20250329_MopenHands_OpenAI-o3-mini-high
MSWE-agent, 20250329_MSWE-agent_OpenAI-o3-mini-high
Go Verified
Source: Multi-SWE-bench Experiments data docs · Mar 2025
MagentLess, 20250329_MagentLess_OpenAI-o3-mini-high
MopenHands, 20250329_MopenHands_OpenAI-o3-mini-high
MSWE-agent, 20250329_MSWE-agent_OpenAI-o3-mini-high
Java Verified
Source: Multi-SWE-bench Experiments data docs · Mar 2025
MagentLess, 20250329_MagentLess_OpenAI-o3-mini-high
MopenHands, 20250329_MopenHands_OpenAI-o3-mini-high
MSWE-agent, 20250329_MSWE-agent_OpenAI-o3-mini-high
JavaScript Verified
Source: Multi-SWE-bench Experiments data docs · Mar 2025
MagentLess, 20250329_MagentLess_OpenAI-o3-mini-high
MopenHands, 20250329_MopenHands_OpenAI-o3-mini-high
MSWE-agent, 20250329_MSWE-agent_OpenAI-o3-mini-high
Lite All Verified
Source: Multi-SWE-bench Experiments data docs · Mar 2025
MagentLess, 20250329_MagentLess_OpenAI-o3-mini-high
MopenHands, 20250329_MopenHands_OpenAI-o3-mini-high
MSWE-agent, 20250329_MSWE-agent_OpenAI-o3-mini-high
Show 9 more resultsHide 9 results
Python Verified
Source: Multi-SWE-bench Experiments data docs · Mar 2025
MagentLess, 20250329_Agentless_OpenAI-o3-mini-high
MopenHands, 20250329_OpenHands_OpenAI-o3-mini-high
MSWE-agent, 20250329_SWE-agent_OpenAI-o3-mini-high
Rust Verified
Source: Multi-SWE-bench Experiments data docs · Mar 2025
MagentLess, 20250329_MagentLess_OpenAI-o3-mini-high
MopenHands, 20250329_MopenHands_OpenAI-o3-mini-high
MSWE-agent, 20250329_MSWE-agent_OpenAI-o3-mini-high
TypeScript Verified
Source: Multi-SWE-bench Experiments data docs · Mar 2025
MagentLess, 20250329_MagentLess_OpenAI-o3-mini-high
MopenHands, 20250329_MopenHands_OpenAI-o3-mini-high
MSWE-agent, 20250329_MSWE-agent_OpenAI-o3-mini-high
SWE-LancerSource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it.

Safety

HELM66 related benchmarks · 66 results
Source: Stanford HELM specialized suites data docs
BenchmarkScore
Safety: BBQ - BBQ accuracy
AIR-Bench: AIRBench 2024 - #1: Confidentiality
AIR-Bench: AIRBench 2024 - #2: Integrity
AIR-Bench: AIRBench 2024 - #3: Availability
Show 62 more benchmarksHide 62 benchmarks
BenchmarkScore
AIR-Bench: AIRBench 2024 - #4: Automated Decision-Making
AIR-Bench: AIRBench 2024 - #5: Autonomous Unsafe Operation of Systems
AIR-Bench: AIRBench 2024 - #6: Advice in Heavily Regulated Industries
AIR-Bench: AIRBench 2024 - #7: Supporting Malicious Organized Groups
AIR-Bench: AIRBench 2024 - #8: Celebrating Suffering
AIR-Bench: AIRBench 2024 - #9: Violent acts
AIR-Bench: AIRBench 2024 - #10: Depicting Violence
AIR-Bench: AIRBench 2024 - #11: Weapon Usage & Development
AIR-Bench: AIRBench 2024 - #12: Military and Warfare
AIR-Bench: AIRBench 2024 - #13: Harassment
AIR-Bench: AIRBench 2024 - #15: Perpetuating Harmful Beliefs
AIR-Bench: AIRBench 2024 - #16: Offensive Language
AIR-Bench: AIRBench 2024 - #17: Adult content
AIR-Bench: AIRBench 2024 - #18: Erotic
AIR-Bench: AIRBench 2024 - #19: Non-Consensual Nudity
AIR-Bench: AIRBench 2024 - #20: Monetized
AIR-Bench: AIRBench 2024 - #21: Endangerment, Harm, or Abuse of Children
AIR-Bench: AIRBench 2024 - #22: Child Sexual Abuse
AIR-Bench: AIRBench 2024 - #23: Suicidal and non-suicidal self Injury
AIR-Bench: AIRBench 2024 - #24: Political Persuasion
AIR-Bench: AIRBench 2024 - #25: Influencing Politics
AIR-Bench: AIRBench 2024 - #26: Deterring Democratic Participation
AIR-Bench: AIRBench 2024 - #27: Disrupting Social Order (China-unique)
AIR-Bench: AIRBench 2024 - #28: High-Risk Financial Activities
AIR-Bench: AIRBench 2024 - #29: Unfair Market Practices
AIR-Bench: AIRBench 2024 - #30: Disempowering Workers
AIR-Bench: AIRBench 2024 - #31: Fraudulent Schemes
AIR-Bench: AIRBench 2024 - #32: Fraud
AIR-Bench: AIRBench 2024 - #33: Academic dishonesty
AIR-Bench: AIRBench 2024 - #34: Mis/disinformation
AIR-Bench: AIRBench 2024 - #35: Sowing Division
AIR-Bench: AIRBench 2024 - #36: Misrepresentation
AIR-Bench: AIRBench 2024 - #37: Types of Defamation
AIR-Bench: AIRBench 2024 - #38: Specific Types of Rights
AIR-Bench: AIRBench 2024 - #39-40: Discrimination/Protected Characteristics Combinations
AIR-Bench: AIRBench 2024 - #41-42: Privacy Violations/Sensitive Data Combinations
AIR-Bench: AIRBench 2024 - #43: Illegal/Regulated substances/goods
AIR-Bench: AIRBench 2024 - #44: Illegal services/exploitation
AIR-Bench: AIRBench 2024 - #45: Other Illegal/Unlawful/Criminal Activities
AIR-Bench: AIRBench 2024 - Child Harm
AIR-Bench: AIRBench 2024 - Criminal Activities
AIR-Bench: AIRBench 2024 - Deception
AIR-Bench: AIRBench 2024 - Defamation
AIR-Bench: AIRBench 2024 - Discrimination/Bias
AIR-Bench: AIRBench 2024 - Economic Harm
AIR-Bench: AIRBench 2024 - Fundamental Rights
AIR-Bench: AIRBench 2024 - Hate/Toxicity
AIR-Bench: AIRBench 2024 - Manipulation
AIR-Bench: AIRBench 2024 - Operational Misuses
AIR-Bench: AIRBench 2024 - Political Usage
AIR-Bench: AIRBench 2024 - Privacy
AIR-Bench: AIRBench 2024 - Refusal Rate
AIR-Bench: AIRBench 2024 - Security Risks
AIR-Bench: AIRBench 2024 - Self-harm
AIR-Bench: AIRBench 2024 - Sexual Content
AIR-Bench: AIRBench 2024 - Violence & Extremism
Safety: Anthropic Red Team - LM Evaluated Safety score
Safety: BBQ - BBQ (ambiguous)
Safety: BBQ - BBQ (unambiguous)
Safety: HarmBench - LM Evaluated Safety score
Safety: SimpleSafetyTests - LM Evaluated Safety score
Safety: XSTest - LM Evaluated Safety score

Human preference

Arena ELO28 related benchmarks · 56 results
Arena ELO
Source: LMArena data · Nov 2026
Reasoning effort
Effort not reported
Arena-Hard-v2.0-Preview
Source: Arena-Hard-Auto data
Creative Writing, Ensemble GPT-4.1 and Gemini 2.5 as Judges (Best Configuration for Creative Writing)
Hard Prompt, Style Control, and Gemini-2.5 as Judge (Official Configuration)
Hard Prompt, Style Control, and GPT-4.1 as Judge (If prefer OpenAI API)
Chinese
Source: LMArena data · Nov 2026
Reasoning effort
Effort not reported
Creative Writing
Source: LMArena data · Nov 2026
Reasoning effort
Effort not reported
English
Source: LMArena data · Nov 2026
Reasoning effort
Effort not reported
Exclude Ties
Source: LMArena data · Nov 2026
Reasoning effort
Effort not reported
Show 43 more resultsHide 43 results
Expert
Source: LMArena data · Nov 2026
Reasoning effort
Effort not reported
French
Source: LMArena data · Nov 2026
Reasoning effort
Effort not reported
German
Source: LMArena data · Nov 2026
Reasoning effort
Effort not reported
Hard Prompts
Source: LMArena data · Nov 2026
Reasoning effort
Effort not reported
Hard Prompts English
Source: LMArena data · Nov 2026
Reasoning effort
Effort not reported
Industry Business and Management and Financial Operations
Source: LMArena data · Nov 2026
Reasoning effort
Effort not reported
Industry Entertainment and Sports and Media
Source: LMArena data · Nov 2026
Reasoning effort
Effort not reported
Industry Life and Physical and Social Science
Source: LMArena data · Nov 2026
Reasoning effort
Effort not reported
Industry Mathematical
Source: LMArena data · Nov 2026
Reasoning effort
Effort not reported
Industry Medicine and Healthcare
Source: LMArena data · Nov 2026
Reasoning effort
Effort not reported
Industry Software and It Services
Source: LMArena data · Nov 2026
Reasoning effort
Effort not reported
Industry Writing and Literature and Language
Source: LMArena data · Nov 2026
Reasoning effort
Effort not reported
Japanese
Source: LMArena data · Nov 2026
Reasoning effort
Effort not reported
Korean
Source: LMArena data · Nov 2026
Reasoning effort
Effort not reported
Longer Query
Source: LMArena data · Nov 2026
Reasoning effort
Effort not reported
Multi Turn
Source: LMArena data · Nov 2026
Reasoning effort
Effort not reported
Non English
Source: LMArena data · Nov 2026
Reasoning effort
Effort not reported
Polish
Source: LMArena data · Nov 2026
Russian
Source: LMArena data · Nov 2026
Reasoning effort
Effort not reported
Spanish
Source: LMArena data · Nov 2026
Reasoning effort
Effort not reported
Style-Controlled
Source: LMArena data · Nov 2026
Reasoning effort
Effort not reported

Math

AIME 2024Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Source: JudgeBench data docs
GPT-4o Dataset, Prompted Judge, Arena-Hard (o3-mini-2025-01-31 (high)), Math Score
GPT-4o Dataset, Prompted Judge, Arena-Hard (o3-mini-2025-01-31 (low)), Math Score
GPT-4o Dataset, Prompted Judge, Arena-Hard (o3-mini-2025-01-31 (medium)), Math Score
LiveBenchSource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
MATHSource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
MGSMSource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
U-MATH7 related benchmarks · 21 results
algebra accuracy
Source: U-MATH and mu-MATH
Task set · algebra · gpt-4o-2024-08-06
differential_calc accuracy
Source: U-MATH and mu-MATH
Task set · differential_calc · gpt-4o-2024-08-06
integral_calc accuracy
Source: U-MATH and mu-MATH
Task set · integral_calc · gpt-4o-2024-08-06
multivariable_calculus accuracy
Source: U-MATH and mu-MATH
Task set · multivariable_calculus · gpt-4o-2024-08-06
overall accuracy
Source: U-MATH and mu-MATH
Task set · u_math · gpt-4o-2024-08-06
precalculus_review accuracy
Source: U-MATH and mu-MATH
Task set · precalculus_review · gpt-4o-2024-08-06
Show 3 more resultsHide 3 results
sequences_series accuracy
Source: U-MATH and mu-MATH
Task set · sequences_series · gpt-4o-2024-08-06
ValsSource: Vals AI

Reasoning

COLLIESource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Source: JudgeBench data docs
GPT-4o Dataset, Prompted Judge, Arena-Hard (o3-mini-2025-01-31 (high)), Reasoning Score
GPT-4o Dataset, Prompted Judge, Arena-Hard (o3-mini-2025-01-31 (low)), Reasoning Score
GPT-4o Dataset, Prompted Judge, Arena-Hard (o3-mini-2025-01-31 (medium)), Reasoning Score

General

Agentic

Science

GPQASource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
PHYBench2 results
Source: PHYBench
Reasoning effort
Effort not reported

Long context

Instruction following

IFEvalSource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Multi-IFSource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim

Factuality

SimpleQASource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim

Knowledge

MMLUSource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim

Multilingual

Speech

Other

Source: JudgeBench data docs
GPT-4o Dataset, Prompted Judge, Arena-Hard (o3-mini-2025-01-31 (high)), Knowledge Score
GPT-4o Dataset, Prompted Judge, Arena-Hard (o3-mini-2025-01-31 (low)), Knowledge Score
GPT-4o Dataset, Prompted Judge, Arena-Hard (o3-mini-2025-01-31 (medium)), Knowledge Score
Source: JudgeBench data docs
GPT-4o Dataset, Prompted Judge, Arena-Hard (o3-mini-2025-01-31 (high)), Overall Score
GPT-4o Dataset, Prompted Judge, Arena-Hard (o3-mini-2025-01-31 (low)), Overall Score
GPT-4o Dataset, Prompted Judge, Arena-Hard (o3-mini-2025-01-31 (medium)), Overall Score
MedHELM33 related benchmarks · 33 results
Nejumi 428 related benchmarks · 28 results
ValsSource: Vals AI

Data credits: Epoch AI Benchmarking Hub, CC BY 4.0 (licence) · Data by LLM Stats · LMArena, CC BY 4.0 (licence) · Arena-Hard-Auto, LMArena, Apache-2.0 (licence) · ArtifactsBench (Tencent Hunyuan), CC BY 4.0 (licence) · BrowserGym Leaderboard (ServiceNow), MIT (licence) · CyBench — cite Zhang et al. 2025 · DABstep (Adyen), CC BY 4.0 (licence) · Stanford HELM (Stanford CRFM); scenario scores from Capabilities, Safety, Long Context, MedHELM, AIR-Bench, MMLU and Finance · JudgeBench, Sijun Tan et al., ScalerLab · LLM Chess by Maxim Saplin, Apache-2.0 (Copyright [2024] [Maxim Saplin]) (licence) · MathArena (ETH SRI / INSAIT), MIT — cite dekoninck2026matharena (licence) · Multi-SWE-bench experiments (multi-swe-bench/experiments), Apache-2.0; resolved-rate fractions converted to percentages (licence) · Nejumi Leaderboard 4, Weights & Biases Japan; public publisher-selected numeric evaluation results · Orak leaderboard, KRAFTON AI (Park et al., NeurIPS 2025). Public numeric scores; leaderboard licence not stated (code MIT not applied; CC BY-NC trajectories not used). · Trishul Lab, PutnamBench public submitted results. Model identities and scaffold budgets preserved; result licence unstated. · SnakeBench (Greg Kamradt / ARC Prize Foundation), MIT (licence) · Swallow LLM Leaderboard v2, Swallow LLM team (Institute of Science Tokyo). Contents CC BY 4.0; Japanese post-trained task scores on the source's 0..1 scale. (licence) · Toloka, U-MATH and mu-MATH public leaderboard. MIT Space; generated solution outputs retain underlying model terms and are not ingested. (licence)

Around the web

Also known as: azure/eu/o3-mini, azure/eu/o3-mini-2025-01-31, azure/o3-mini, azure/o3-mini-2025-01-31, azure/us-gov/o3-mini, azure/us-gov/o3-mini-2025-01-31, azure/us/o3-mini, azure/us/o3-mini-2025-01-31, gradient_ai/openai-o3-mini, o3-mini-0131, o3-mini-2025-01-31, o3-mini-2025-01-31-high, o3-mini-2025-01-31-low, o3-mini-high, o3-mini-low, openai-o3-mini, openai/o3-mini, openai/o3-mini-high, openai/o3-mini:batch, vercel_ai_gateway/openai/o3-mini

Like this one. Tap or hover any dotted value, label or icon to see where it comes from and how it is measured. open details when tapped or hovered. How this data works