Enter opens the highlighted result. Esc closes.

GPT-4o-mini vs o1

Updated October 21, 2026. 19 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.

Replace GPT-4o-mini Replace o1
GPT-4o-miniOpenAI
Coding
No data
Overall
6.7
Output $/M
$0.60
0
o1OpenAI
Coding
No data
Overall
15.2
Output $/M
$60.00
19
vs boards won of 19 shared

Decision reading

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

GPT-4o-mini has the edge where output tokens cost 100.0x less, and where what matters is AA Coding Index or LiveCodeBench (Vals AI), where it leads.

Model AGPT-4o-miniOpenAINot benchmarkedNo coding benchmarkNo cost per solved taskModel Bo1OpenAINot benchmarkedNo coding benchmarkNo cost per solved task
Shared results
19
GPT-4o-mini only
8
o1 only
49
Like-for-like categories
6 of 9

Shared results can support a head-to-head reading. Results only one model has describe coverage, not superiority.

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
GPT-4o-mini not benchmarked, o1 not benchmarked.
Widest category
Coding, 32.2 points apart on average over 3 shared benchmarks.
Widest single gap
AIME: GPT-4o-mini 11.5% against o1 71.5%, 60.0 points apart on a 0 to 100 scale.
Output price
GPT-4o-mini $0.60 against o1 $60.00 per million output tokens, 100.0x apart.
Context window
GPT-4o-mini takes 128K tokens, o1 200K.

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
CategoryGPT-4o-miniBarso1Ties
Coding03
Intelligence02
Reasoning04
Math03
Knowledge04
General03
All shared boards019
CodingLike-for-likeSix of these boards feed the Vibe Coding Index03
Coding benchmarks for GPT-4o-mini and o1
BenchmarkGPT-4o-minio1Leader
Aider polyglotNot measured61.7%Only o1 measured
AA Coding Index11.439.7o1
LiveCodeBench (Vals AI)26.4%50.3%o1
LiveCodeBench (Artificial Analysis run)23.4%67.9%o1
Terminal-Bench Hard (Artificial Analysis run)Not measured12.9%Only o1 measured
WeirdMLNot measured46.1%Only o1 measured
LMArena Text: codingNot measured1367Only o1 measured
LMArena Text: software and ITNot measured1366Only o1 measured
Neither model has a result on the other 30 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
Intelligence benchmarks for GPT-4o-mini and o1
BenchmarkGPT-4o-minio1Leader
AA Intelligence Index6.715.2o1
Epoch Capabilities Index126.5141.7o1
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index2 boards, none shared
Agentic work benchmarks for GPT-4o-mini and o1
BenchmarkGPT-4o-minio1Leader
τ²-Bench TelecomNot measured62.6%Only o1 measured
METR time horizonsNot measured51.1%Only o1 measured
Neither model has a result on the other 37 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index04
Reasoning benchmarks for GPT-4o-mini and o1
BenchmarkGPT-4o-minio1Leader
GPQA Diamond44.2%73.2%o1
MMMU Pro (Vals AI)56.6%77.4%o1
GPQA Diamond (Artificial Analysis run)42.6%74.7%o1
Humanity's Last Exam (Artificial Analysis run)4.2%7.0%o1
GPQA Diamond (Epoch AI run)Not measured76.8%Only o1 measured
ARC-AGINot measured30.7%Only o1 measured
ARC-AGI-20.0%Not measuredOnly GPT-4o-mini measured
SimpleBenchNot measured40.1%Only o1 measured
Chess puzzlesNot measured10.0%Only o1 measured
VPCTNot measured37.0%Only o1 measured
LMArena Text: hard promptsNot measured1371Only o1 measured
LMArena Text: expertNot measured1361Only o1 measured
LMArena Text: hard prompts in EnglishNot measured1372Only o1 measured
Neither model has a result on the other 8 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index03
Math benchmarks for GPT-4o-mini and o1
BenchmarkGPT-4o-minio1Leader
AIME11.5%71.5%o1
MATH 500 (Vals AI)72.6%90.4%o1
MGSM (Vals AI)86.2%89.3%o1
AA Math Index14.7Not measuredOnly GPT-4o-mini measured
AIME 2025 (Artificial Analysis run)14.7%Not measuredOnly GPT-4o-mini measured
OTIS Mock AIMENot measured73.3%Only o1 measured
FrontierMath, tiers 1 to 3Not measured14.7%Only o1 measured
MATH level 5Not measured94.7%Only o1 measured
GSM8K91.3%Not measuredOnly GPT-4o-mini measured
LMArena Text: mathNot measured1388Only o1 measured
LMArena Text: mathematical workNot measured1390Only o1 measured
Neither model has a result on the other 2 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index04
Knowledge benchmarks for GPT-4o-mini and o1
BenchmarkGPT-4o-minio1Leader
MMLU Pro62.7%83.5%o1
LegalBench (Vals AI)Not measured80.4%Only o1 measured
CorpFin (Vals AI)45.5%Not measuredOnly GPT-4o-mini measured
TaxEval (Vals AI)60.5%74.3%o1
MortgageTax (Vals AI)54.5%Not measuredOnly GPT-4o-mini measured
MedQA (Vals AI)72.4%96.5%o1
MMLU Pro (Artificial Analysis run)64.8%84.1%o1
SimpleQA VerifiedNot measured41.1%Only o1 measured
MMLU81.8%Not measuredOnly GPT-4o-mini measured
GeoBenchNot measured80.0%Only o1 measured
LMArena Text: scienceNot measured1369Only o1 measured
LMArena Text: medicine and healthcareNot measured1355Only o1 measured
LMArena Text: legal and governmentNot measured1368Only o1 measured
LMArena Text: business and financeNot measured1328Only o1 measured
Neither model has a result on the other 3 boards here
Web designNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Web design benchmarks for GPT-4o-mini and o1
BenchmarkGPT-4o-minio1Leader
Neither model has a result on 9 boards here
GeneralLike-for-likePublic boards, shown as published, kept out of the index03
General benchmarks for GPT-4o-mini and o1
BenchmarkGPT-4o-minio1Leader
IFBench31.0%70.3%o1
Long context reasoning (AA-LCR)Not measured65.0%Only o1 measured
DTBench54.4%74.7%o1
LMCA10.4%22.3%o1
Fiction.LiveBenchNot measured83.3%Only o1 measured
Creative writing (Lech Mazur)Not measured70.2%Only o1 measured
PIQA88.7%Not measuredOnly GPT-4o-mini measured
LMArena TextNot measured1366Only o1 measured
LMArena Text: instruction followingNot measured1367Only o1 measured
LMArena Text: creative writingNot measured1347Only o1 measured
LMArena VisionNot measured1168Only o1 measured
LMArena Text: EnglishNot measured1372Only o1 measured
LMArena Text: non-EnglishNot measured1358Only o1 measured
LMArena Text: ChineseNot measured1394Only o1 measured
LMArena Text: GermanNot measured1337Only o1 measured
LMArena Text: JapaneseNot measured1346Only o1 measured
LMArena Text: KoreanNot measured1396Only o1 measured
LMArena Text: FrenchNot measured1344Only o1 measured
LMArena Text: SpanishNot measured1345Only o1 measured
LMArena Text: RussianNot measured1356Only o1 measured
LMArena Text: multi-turnNot measured1355Only o1 measured
LMArena Text: longer queriesNot measured1378Only o1 measured
LMArena Text: writing and languageNot measured1360Only o1 measured
LMArena Text: entertainment and mediaNot measured1358Only o1 measured
LMArena Vision: EnglishNot measured1162Only o1 measured
LMArena Vision: ChineseNot measured1235Only 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 GPT-4o-mini and o1
BenchmarkGPT-4o-minio1Leader
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

GPT-4o-mini$0.0004Fits in one request
o1$0.045Fits in one request

GPT-4o-mini costs less

Repository review

50K input + 3K output tokens

GPT-4o-mini$0.0093Fits in one request
o1$0.930Fits in one request

GPT-4o-mini costs less

Agent loop

200K input + 10K output tokens

GPT-4o-mini$0.036Exceeds the context window
o1$3.60Exceeds the context window

GPT-4o-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 GPT-4o-mini and o1
SpecificationOpenAI GPT-4o-miniOpenAI o1
MakerOpenAIOpenAI
WeightsNo public weights listedNo public weights listed
ReleasedJuly 18, 2024December 17, 2024
Context window128K200K
Input $/Mtok$0.15$15.00
Output $/Mtok$0.60$60.00
Coding indexNot benchmarkedNot benchmarked
Independent measurements behind it00
Cost per solved taskNot computableNot computable
SourceOpenRouter listingOpenRouter listing

Questions

Is GPT-4o-mini better than o1 for coding?

Neither model has a coding score yet, so the two cannot be ranked on coding. GPT-4o-mini has the edge where output tokens cost 100.0x less, and where what matters is AA Coding Index or LiveCodeBench (Vals AI), where it leads.

Which is cheaper, GPT-4o-mini or o1?

GPT-4o-mini costs $0.15 per million input tokens and $0.60 per million output tokens; o1 costs $15.00 and $60.00. Cost per solved task is known for neither of them.

Which has the bigger context window, GPT-4o-mini or o1?

o1, with 200K tokens against 128K.

How many benchmarks is the GPT-4o-mini vs o1 comparison based on?

19 benchmarks have a result for both models as of October 21, 2026. GPT-4o-mini's coding index rests on 0 independent benchmarks and o1's on 0. Where only one model has a result, the page says so instead of naming a winner.

Compare next