Enter opens the highlighted result. Esc closes.

o1 vs o3 Mini

o1 leads o3 Mini on the Artificial Analysis Intelligence Index, 15.2 to 12.5, and o3 Mini costs 13.6x less per output token ($4.40 vs $60.00 per million). Updated October 22, 2026; 61 benchmarks have a result for both.

Replace o1 Replace o3 Mini
o1OpenAI
Coding
No data
Overall
44.6
Output $/M
$60.00
41
o3 MiniOpenAI
Coding
No data
Overall
38.0
Output $/M
$4.40
20
vs boards won of 61 shared

o1 or o3 Mini: which to pick

Neither model has a coding score yet, so the two cannot be ranked on coding.

Pick o1 for work measured by LiveCodeBench (Vals AI) or LiveCodeBench (Artificial Analysis run), where it leads.

Model Ao1OpenAINot benchmarkedNo coding benchmarkNo cost per solved taskModel Bo3 MiniOpenAINot benchmarkedNo coding benchmarkNo cost per solved task
Shared results
61
o1 only
8
o3 Mini only
10
Like-for-like categories
7 of 9

Only benchmarks that tested both models count toward a pick; a result only one model has is shown but not compared.

Which one for your work

Each card is decided by one number both models carry. Where only one has it, the card says so and makes no call.

At a glance

Coding index
o1 not benchmarked, o3 Mini not benchmarked.
Widest category
Agentic work, 31.3 points apart on average over 1 shared benchmark.
Widest single gap
Fiction.LiveBench: o1 83.3% against o3 Mini 50.0%, 33.3 points apart on a 0 to 100 scale.
Output price
o1 $60.00 against o3 Mini $4.40 per million output tokens, 13.6x apart.
Context window
Both take 200K tokens.

Benchmark by benchmark

First the score: boards each model leads, per category, where both have a result. Then every board, a category to a fold; bars are each result on a 0 to 100 scale, so compare the two in a row, not one row with another.

Boards won, where both have a result
Categoryo1Barso3 MiniTies
Coding44
Intelligence20
Agentic work10
Reasoning28
Math08
Knowledge100
General220
All shared boards4120
CodingLike-for-likeSix of these boards feed the Vibe Coding Index44
Coding benchmarks for o1 and o3 Mini
Benchmarko1o3 MiniLeader
Aider polyglot61.7%60.4%o1
SWE-bench VerifiedNot measured42.4%Only o3 Mini measured
SWE-bench LiteNot measured32.3%Only o3 Mini measured
AA Coding Index39.7Not measuredOnly o1 measured
LiveCodeBench (Vals AI)50.3%71.5%o3 Mini
LiveCodeBench (Artificial Analysis run)67.9%73.4%o3 Mini
SciCodeNot measured42.8%Only o3 Mini measured
Terminal-Bench Hard (Artificial Analysis run)12.9%6.8%o1
GSO-BenchNot measured1.3%Only o3 Mini measured
WeirdML46.1%43.7%o1
CybenchNot measured22.5%Only o3 Mini measured
LMArena Text: coding13671378o3 Mini
LMArena Text: software and IT13661364o1
SciCode4.6%7.7%o3 Mini
Neither model has a result on the other 25 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
Intelligence benchmarks for o1 and o3 Mini
Benchmarko1o3 MiniLeader
AA Intelligence Index15.212.5o1
Epoch Capabilities Index141.7140.2o1
Agentic workLike-for-likePublic boards, shown as published, kept out of the index10
Agentic work benchmarks for o1 and o3 Mini
Benchmarko1o3 MiniLeader
τ²-Bench Telecom62.6%31.3%o1
METR time horizons51.1%Not measuredOnly o1 measured
Neither model has a result on the other 39 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index28
Reasoning benchmarks for o1 and o3 Mini
Benchmarko1o3 MiniLeader
GPQA Diamond73.2%75.5%o3 Mini
MMMU Pro (Vals AI)77.4%Not measuredOnly o1 measured
GPQA Diamond (Artificial Analysis run)74.7%77.3%o3 Mini
Humanity's Last Exam (Artificial Analysis run)7.0%12.0%o3 Mini
GPQA Diamond (Epoch AI run)76.8%77.0%o3 Mini
ARC-AGI30.7%34.5%o3 Mini
ARC-AGI-2Not measured3.0%Only o3 Mini measured
SimpleBench40.1%22.8%o1
Chess puzzles10.0%15.0%o3 Mini
Mystery game puzzlesNot measured7.0%Only o3 Mini measured
VPCT37.0%Not measuredOnly o1 measured
LMArena Text: hard prompts13711365o1
LMArena Text: expert13611364o3 Mini
LMArena Text: hard prompts in English13721375o3 Mini
Neither model has a result on the other 8 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index08
Math benchmarks for o1 and o3 Mini
Benchmarko1o3 MiniLeader
AIME71.5%86.5%o3 Mini
MATH 500 (Vals AI)90.4%91.8%o3 Mini
MGSM (Vals AI)89.3%91.3%o3 Mini
OTIS Mock AIME73.3%76.9%o3 Mini
FrontierMath, tiers 1 to 314.7%18.6%o3 Mini
FrontierMath, tier 4Not measured0.0%Only o3 Mini measured
MATH level 594.7%96.5%o3 Mini
LMArena Text: math13881396o3 Mini
LMArena Text: mathematical work13901399o3 Mini
Neither model has a result on the other 4 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index100
Knowledge benchmarks for o1 and o3 Mini
Benchmarko1o3 MiniLeader
MMLU Pro83.5%78.7%o1
LegalBench (Vals AI)80.4%71.5%o1
CorpFin (Vals AI)Not measured45.3%Only o3 Mini measured
TaxEval (Vals AI)74.3%69.4%o1
MedQA (Vals AI)96.5%94.8%o1
MMLU Pro (Artificial Analysis run)84.1%80.2%o1
SimpleQA Verified41.1%15.3%o1
GeoBench80.0%Not measuredOnly o1 measured
LMArena Text: science13691339o1
LMArena Text: medicine and healthcare13551330o1
LMArena Text: legal and government13681328o1
LMArena Text: business and finance13281313o1
Neither model has a result on the other 6 boards here
Web designNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Web design benchmarks for o1 and o3 Mini
Benchmarko1o3 MiniLeader
Neither model has a result on 9 boards here
GeneralLike-for-likePublic boards, shown as published, kept out of the index220
General benchmarks for o1 and o3 Mini
Benchmarko1o3 MiniLeader
IFBench70.3%67.1%o1
Long context reasoning (AA-LCR)65.0%43.0%o1
DTBench74.7%68.8%o1
LMCA22.3%19.0%o1
Fiction.LiveBench83.3%50.0%o1
Creative writing (Lech Mazur)70.2%61.7%o1
LMArena Text13661337o1
LMArena Text: instruction following13671337o1
LMArena Text: creative writing13471286o1
LMArena Vision1168Not measuredOnly o1 measured
LMArena Text: English13721351o1
LMArena Text: non-English13581319o1
LMArena Text: Chinese13941379o1
LMArena Text: German13371303o1
LMArena Text: Japanese13461286o1
LMArena Text: Korean13961313o1
LMArena Text: French13441334o1
LMArena Text: Spanish13451321o1
LMArena Text: Russian13561304o1
LMArena Text: PolishNot measured1294Only o3 Mini measured
LMArena Text: multi-turn13551320o1
LMArena Text: longer queries13781343o1
LMArena Text: writing and language13601313o1
LMArena Text: entertainment and media13581283o1
LMArena Vision: English1162Not measuredOnly o1 measured
LMArena Vision: Chinese1235Not measuredOnly o1 measured
Neither model has a result on the other 20 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for o1 and o3 Mini
Benchmarko1o3 MiniLeader
Neither model has a result on 5 boards here

What each workload costs

Three fixed token mixes at each model's listed price, so per-token rates become a bill.

Chat turn

1K input + 500 output tokens

o1$0.045Fits in one request
o3 Mini$0.0033Fits in one request

o3 Mini costs less

Repository review

50K input + 3K output tokens

o1$0.930Fits in one request
o3 Mini$0.068Fits in one request

o3 Mini costs less

Agent loop

200K input + 10K output tokens

o1$3.60Exceeds the context window
o3 Mini$0.264Exceeds the context window

o3 Mini costs less

Listed OpenRouter rates, without cache or batch discounts. A workload that does not fit a model's context window would need splitting.

Specification differences

The leading value in a row is marked; a row with a missing value names no leader. Our two rows are marked in red.

Specifications of o1 and o3 Mini
SpecificationOpenAI o1OpenAI o3 Mini
MakerOpenAIOpenAI
WeightsNo public weights listedNo public weights listed
ReleasedDecember 17, 2024January 31, 2025
Context window200K200K
Input $/Mtok$15.00$1.10
Output $/Mtok$60.00$4.40
Coding indexNot benchmarkedNot benchmarked
Independent measurements behind it00
Cost per solved taskNot computableNot computable
SourceOpenRouter listingOpenRouter listing

Questions

Is o1 better than o3 Mini for coding?

Neither model has a coding score yet, so the two cannot be ranked on coding. Pick o1 for work measured by LiveCodeBench (Vals AI) or LiveCodeBench (Artificial Analysis run), where it leads.

Which is cheaper, o1 or o3 Mini?

o1 costs $15.00 per million input tokens and $60.00 per million output tokens; o3 Mini costs $1.10 and $4.40. Cost per solved task is known for neither of them.

Which has the bigger context window, o1 or o3 Mini?

Neither: both take 200K tokens.

How many benchmarks is the o1 vs o3 Mini comparison based on?

61 benchmarks have a result for both models as of October 22, 2026. o1's coding index rests on 0 independent benchmarks and o3 Mini's on 0. Where only one model has a result, the page says so instead of naming a winner.

Compare next