Enter opens the highlighted result. Esc closes.

o1 vs o3

o3 leads o1 on the Artificial Analysis Intelligence Index, 20.2 to 15.2, and o3 costs 7.5x less per output token ($8.00 vs $60.00 per million). Updated October 22, 2026; 68 benchmarks have a result for both.

Replace o1 Replace o3
o1OpenAI
Coding
No data
Overall
44.6
Output $/M
$60.00
4
o3OpenAI
Coding
No data
Overall
51.1
Output $/M
$8.00
64
vs boards won of 68 shared

o1 or o3: which to pick

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

Pick o1 for work measured by Aider polyglot or LiveCodeBench (Vals AI), where it leads.

Model Ao1OpenAINot benchmarkedNo coding benchmarkNo cost per solved taskModel Bo3OpenAINot benchmarkedNo coding benchmark$0.571 per solved task
Shared results
68
o1 only
1
o3 only
34
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 not benchmarked.
Widest category
Agentic work, 16.3 points apart on average over 2 shared benchmarks.
Widest single gap
LiveCodeBench (Vals AI): o1 50.3% against o3 83.9%, 33.7 points apart on a 0 to 100 scale.
Output price
o1 $60.00 against o3 $8.00 per million output tokens, 7.5x 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
Categoryo1Barso3Ties
Coding08
Intelligence02
Agentic work02
Reasoning012
Math08
Knowledge29
General223
All shared boards464
CodingLike-for-likeSix of these boards feed the Vibe Coding Index08
Coding benchmarks for o1 and o3
Benchmarko1o3Leader
Aider polyglot61.7%81.3%o3
SWE-bench VerifiedNot measured58.4%Only o3 measured
SWE-bench MultimodalNot measured36.0%Only o3 measured
AA Coding Index39.7Not measuredOnly o1 measured
LiveCodeBench (Vals AI)50.3%83.9%o3
LiveCodeBench (Artificial Analysis run)67.9%80.8%o3
Terminal-Bench Hard (Artificial Analysis run)12.9%37.1%o3
GSO-BenchNot measured8.8%Only o3 measured
WeirdML46.1%52.4%o3
ALE-BenchNot measured933.5Only o3 measured
LMArena Text: coding13671407o3
LMArena Text: software and IT13661415o3
SciCode4.6%9.2%o3
Neither model has a result on the other 26 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
Intelligence benchmarks for o1 and o3
Benchmarko1o3Leader
AA Intelligence Index15.220.2o3
Epoch Capabilities Index141.7146.7o3
Agentic workLike-for-likePublic boards, shown as published, kept out of the index02
Agentic work benchmarks for o1 and o3
Benchmarko1o3Leader
τ²-Bench Telecom62.6%80.7%o3
METR time horizons51.1%65.4%o3
GDPvalNot measured30.8%Only o3 measured
DeepResearch BenchNot measured45.2%Only o3 measured
OSWorldNot measured23.0%Only o3 measured
Berkeley Function Calling Leaderboard (BFCL)Not measured63.0%Only o3 measured
BrowseComp-PlusNot measured65.9%Only o3 measured
Neither model has a result on the other 34 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index012
Reasoning benchmarks for o1 and o3
Benchmarko1o3Leader
GPQA Diamond73.2%84.1%o3
MMMU Pro (Vals AI)77.4%80.4%o3
GPQA Diamond (Artificial Analysis run)74.7%82.7%o3
Humanity's Last Exam (Artificial Analysis run)7.0%20.1%o3
GPQA Diamond (Epoch AI run)76.8%81.8%o3
ARC-AGI30.7%60.8%o3
ARC-AGI-2Not measured6.5%Only o3 measured
SimpleBench40.1%53.1%o3
Chess puzzles10.0%37.0%o3
Mystery game puzzlesNot measured29.0%Only o3 measured
VPCT37.0%52.0%o3
LMArena Text: hard prompts13711402o3
LMArena Text: expert13611402o3
LMArena Text: hard prompts in English13721411o3
LMArena Vision: diagramsNot measured1220Only o3 measured
LMArena Vision: homeworkNot measured1234Only o3 measured
Kagi LLM BenchmarkNot measured67.6%Only o3 measured
Neither model has a result on the other 5 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index08
Math benchmarks for o1 and o3
Benchmarko1o3Leader
AIME71.5%85.3%o3
MATH 500 (Vals AI)90.4%94.6%o3
MGSM (Vals AI)89.3%91.8%o3
AA Math IndexNot measured88.3Only o3 measured
AIME 2025 (Artificial Analysis run)Not measured88.3%Only o3 measured
OTIS Mock AIME73.3%84.4%o3
FrontierMath, tiers 1 to 314.7%33.3%o3
MATH level 594.7%97.8%o3
LMArena Text: math13881426o3
LMArena Text: mathematical work13901423o3
Neither model has a result on the other 3 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index29
Knowledge benchmarks for o1 and o3
Benchmarko1o3Leader
MMLU Pro83.5%85.6%o3
LegalBench (Vals AI)80.4%83.8%o3
CorpFin (Vals AI)Not measured59.7%Only o3 measured
TaxEval (Vals AI)74.3%74.6%o3
MortgageTax (Vals AI)Not measured65.7%Only o3 measured
MedQA (Vals AI)96.5%96.1%o1
MedCode (Vals AI)Not measured47.3%Only o3 measured
MMLU Pro (Artificial Analysis run)84.1%85.3%o3
SimpleQA Verified41.1%49.4%o3
GeoBench80.0%74.0%o1
LMArena Text: science13691429o3
LMArena Text: medicine and healthcare13551448o3
LMArena Text: legal and government13681428o3
LMArena Text: business and finance13281393o3
FACTS Benchmark SuiteNot measured44.4%Only o3 measured
Neither model has a result on the other 3 boards here
Web designDirectional onlyPublic boards, shown as published, kept out of the index5 boards, none shared
Web design benchmarks for o1 and o3
Benchmarko1o3Leader
Design Arena: websitesNot measured1036Only o3 measured
Design Arena: UI componentsNot measured1017Only o3 measured
Design Arena: game devNot measured1034Only o3 measured
Design Arena: data vizNot measured1200Only o3 measured
Design Arena: all code categoriesNot measured1020Only o3 measured
Neither model has a result on the other 4 boards here
GeneralLike-for-likePublic boards, shown as published, kept out of the index223
General benchmarks for o1 and o3
Benchmarko1o3Leader
SAGE (Vals AI)Not measured41.8%Only o3 measured
MedScribe (Vals AI)Not measured76.7%Only o3 measured
IFBench70.3%71.4%o3
Long context reasoning (AA-LCR)65.0%74.7%o3
DTBench74.7%84.8%o3
LMCA22.3%39.7%o3
Fiction.LiveBench83.3%88.9%o3
Creative writing (Lech Mazur)70.2%83.9%o3
CL-benchNot measured17.8%Only o3 measured
LMArena Text13661410o3
LMArena Text: instruction following13671368o3
LMArena Text: creative writing13471359o3
LMArena Vision11681214o3
LMArena Text: English13721417o3
LMArena Text: non-English13581401o3
LMArena Text: Chinese13941437o3
LMArena Text: German13371420o3
LMArena Text: Japanese13461403o3
LMArena Text: Korean13961370o1
LMArena Text: French13441430o3
LMArena Text: Spanish13451395o3
LMArena Text: Russian13561406o3
LMArena Text: PolishNot measured1438Only o3 measured
LMArena Text: multi-turn13551405o3
LMArena Text: longer queries13781372o1
LMArena Text: writing and language13601372o3
LMArena Text: entertainment and media13581373o3
LMArena Vision: English11621221o3
LMArena Vision: Chinese12351237o3
LMArena Vision: reading textNot measured1218Only o3 measured
LMArena Vision: humorNot measured1222Only o3 measured
LMArena Vision: captioningNot measured1210Only o3 measured
LMArena Vision: recognizing thingsNot measured1234Only o3 measured
LMArena Vision: creative writingNot measured1201Only o3 measured
Neither model has a result on the other 12 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for o1 and o3
Benchmarko1o3Leader
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$0.0060Fits in one request

o3 costs less

Repository review

50K input + 3K output tokens

o1$0.930Fits in one request
o3$0.124Fits in one request

o3 costs less

Agent loop

200K input + 10K output tokens

o1$3.60Exceeds the context window
o3$0.480Exceeds the context window

o3 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
SpecificationOpenAI o1OpenAI o3
MakerOpenAIOpenAI
WeightsNo public weights listedNo public weights listed
ReleasedDecember 17, 2024April 16, 2025
Context window200K200K
Input $/Mtok$15.00$2.00
Output $/Mtok$60.00$8.00
Coding indexNot benchmarkedNot benchmarked
Independent measurements behind it00
Cost per solved taskNot computable$0.571
SourceOpenRouter listingOpenRouter listing

Questions

Is o1 better than o3 for coding?

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

Which is cheaper, o1 or o3?

o1 costs $15.00 per million input tokens and $60.00 per million output tokens; o3 costs $2.00 and $8.00. Cost per solved task is known for o3 only.

Which has the bigger context window, o1 or o3?

Neither: both take 200K tokens.

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

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

Compare next