Enter opens the highlighted result. Esc closes.

GPT-4 vs o3 Mini

o3 Mini leads GPT-4 on the Artificial Analysis Intelligence Index, 12.5 to 6.7, and o3 Mini costs 13.6x less per output token ($4.40 vs $60.00 per million). Updated October 22, 2026; 37 benchmarks have a result for both.

Replace GPT-4 Replace o3 Mini
GPT-4OpenAI
Coding
No data
Overall
No data
Output $/M
$60.00
1
o3 MiniOpenAI
Coding
No data
Overall
38.0
Output $/M
$4.40
36
vs boards won of 37 shared

GPT-4 or o3 Mini: which to pick

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

Pick GPT-4 for work measured by SWE-bench Verified or LMArena Text: coding, where it leads.

Model AGPT-4OpenAINot benchmarkedNo coding benchmarkNo cost per solved taskModel Bo3 MiniOpenAINot benchmarkedNo coding benchmarkNo cost per solved task
Shared results
37
GPT-4 only
8
o3 Mini only
34
Like-for-like categories
6 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
GPT-4 not benchmarked, o3 Mini not benchmarked.
Widest category
Reasoning, 33.4 points apart on average over 4 shared benchmarks.
Widest single gap
GPQA Diamond (Artificial Analysis run): GPT-4 34.9% against o3 Mini 77.3%, 42.4 points apart on a 0 to 100 scale.
Output price
GPT-4 $60.00 against o3 Mini $4.40 per million output tokens, 13.6x apart.
Context window
GPT-4 takes 8K tokens, o3 Mini 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-4Barso3 MiniTies
Coding13
Intelligence02
Reasoning04
Math02
Knowledge05
General020
All shared boards136
CodingLike-for-likeSix of these boards feed the Vibe Coding Index13
Coding benchmarks for GPT-4 and o3 Mini
BenchmarkGPT-4o3 MiniLeader
Aider polyglotNot measured60.4%Only o3 Mini measured
SWE-bench Verified22.4%42.4%o3 Mini
SWE-bench Lite39.7%32.3%GPT-4
SWE-bench (full test set)12.5%Not measuredOnly GPT-4 measured
AA Coding Index13.1Not measuredOnly GPT-4 measured
LiveCodeBench (Vals AI)Not measured71.5%Only o3 Mini measured
LiveCodeBench (Artificial Analysis run)Not measured73.4%Only o3 Mini measured
SciCodeNot measured42.8%Only o3 Mini measured
Terminal-Bench Hard (Artificial Analysis run)Not measured6.8%Only o3 Mini measured
GSO-BenchNot measured1.3%Only o3 Mini measured
WeirdMLNot measured43.7%Only o3 Mini measured
CybenchNot measured22.5%Only o3 Mini measured
LMArena Text: coding12091378o3 Mini
LMArena Text: software and IT11951364o3 Mini
SciCodeNot measured7.7%Only o3 Mini measured
Neither model has a result on the other 24 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
Intelligence benchmarks for GPT-4 and o3 Mini
BenchmarkGPT-4o3 MiniLeader
AA Intelligence Index6.712.5o3 Mini
Epoch Capabilities Index125.7140.2o3 Mini
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index1 board, none shared
Agentic work benchmarks for GPT-4 and o3 Mini
BenchmarkGPT-4o3 MiniLeader
τ²-Bench TelecomNot measured31.3%Only o3 Mini measured
Neither model has a result on the other 40 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index04
Reasoning benchmarks for GPT-4 and o3 Mini
BenchmarkGPT-4o3 MiniLeader
GPQA DiamondNot measured75.5%Only o3 Mini measured
GPQA Diamond (Artificial Analysis run)34.9%77.3%o3 Mini
Humanity's Last Exam (Artificial Analysis run)Not measured12.0%Only o3 Mini measured
GPQA Diamond (Epoch AI run)Not measured77.0%Only o3 Mini measured
ARC-AGINot measured34.5%Only o3 Mini measured
ARC-AGI-2Not measured3.0%Only o3 Mini measured
SimpleBenchNot measured22.8%Only o3 Mini measured
Chess puzzlesNot measured15.0%Only o3 Mini measured
Mystery game puzzlesNot measured7.0%Only o3 Mini measured
BIG-Bench Hard75.1%Not measuredOnly GPT-4 measured
LMArena Text: hard prompts12001365o3 Mini
LMArena Text: expert11491364o3 Mini
LMArena Text: hard prompts in English12091375o3 Mini
Neither model has a result on the other 9 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index02
Math benchmarks for GPT-4 and o3 Mini
BenchmarkGPT-4o3 MiniLeader
AIMENot measured86.5%Only o3 Mini measured
MATH 500 (Vals AI)Not measured91.8%Only o3 Mini measured
MGSM (Vals AI)Not measured91.3%Only o3 Mini measured
OTIS Mock AIMENot measured76.9%Only o3 Mini measured
FrontierMath, tiers 1 to 3Not measured18.6%Only o3 Mini measured
FrontierMath, tier 4Not measured0.0%Only o3 Mini measured
MATH level 5Not measured96.5%Only o3 Mini measured
GSM8K92.0%Not measuredOnly GPT-4 measured
LMArena Text: math12301396o3 Mini
LMArena Text: mathematical work12281399o3 Mini
Neither model has a result on the other 3 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index05
Knowledge benchmarks for GPT-4 and o3 Mini
BenchmarkGPT-4o3 MiniLeader
MMLU ProNot measured78.7%Only o3 Mini measured
LegalBench (Vals AI)Not measured71.5%Only o3 Mini measured
CorpFin (Vals AI)Not measured45.3%Only o3 Mini measured
TaxEval (Vals AI)Not measured69.4%Only o3 Mini measured
MedQA (Vals AI)Not measured94.8%Only o3 Mini measured
MMLU Pro (Artificial Analysis run)56.2%80.2%o3 Mini
SimpleQA VerifiedNot measured15.3%Only o3 Mini measured
MMLU86.4%Not measuredOnly GPT-4 measured
AI2 Reasoning Challenge96.3%Not measuredOnly GPT-4 measured
LMArena Text: science11771339o3 Mini
LMArena Text: medicine and healthcare11451330o3 Mini
LMArena Text: legal and government11911328o3 Mini
LMArena Text: business and finance11451313o3 Mini
Neither model has a result on the other 5 boards here
Web designNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Web design benchmarks for GPT-4 and o3 Mini
BenchmarkGPT-4o3 MiniLeader
Neither model has a result on 9 boards here
GeneralLike-for-likePublic boards, shown as published, kept out of the index020
General benchmarks for GPT-4 and o3 Mini
BenchmarkGPT-4o3 MiniLeader
IFBench33.2%67.1%o3 Mini
Long context reasoning (AA-LCR)Not measured43.0%Only o3 Mini measured
DTBench62.7%68.8%o3 Mini
LMCA17.1%19.0%o3 Mini
Fiction.LiveBenchNot measured50.0%Only o3 Mini measured
Creative writing (Lech Mazur)Not measured61.7%Only o3 Mini measured
HellaSwag95.3%Not measuredOnly GPT-4 measured
WinoGrande87.5%Not measuredOnly GPT-4 measured
LMArena Text12061337o3 Mini
LMArena Text: instruction following12011337o3 Mini
LMArena Text: creative writing11911286o3 Mini
LMArena Text: English12201351o3 Mini
LMArena Text: non-English11941319o3 Mini
LMArena Text: Chinese11841379o3 Mini
LMArena Text: German11981303o3 Mini
LMArena Text: Japanese11371286o3 Mini
LMArena Text: Korean10871313o3 Mini
LMArena Text: French12201334o3 Mini
LMArena Text: Spanish11971321o3 Mini
LMArena Text: Russian11951304o3 Mini
LMArena Text: Polish12651294o3 Mini
LMArena Text: multi-turn12061320o3 Mini
LMArena Text: longer queries11901343o3 Mini
LMArena Text: writing and language12191313o3 Mini
LMArena Text: entertainment and media11841283o3 Mini
Neither model has a result on the other 21 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for GPT-4 and o3 Mini
BenchmarkGPT-4o3 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

GPT-4$0.060Fits in one request
o3 Mini$0.0033Fits in one request

o3 Mini costs less

Repository review

50K input + 3K output tokens

GPT-4$1.68Exceeds the context window
o3 Mini$0.068Fits in one request

o3 Mini costs less

Agent loop

200K input + 10K output tokens

GPT-4$6.60Exceeds 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 GPT-4 and o3 Mini
SpecificationOpenAI GPT-4OpenAI o3 Mini
MakerOpenAIOpenAI
WeightsNo public weights listedNo public weights listed
ReleasedMay 28, 2023January 31, 2025
Context window8K200K
Input $/Mtok$30.00$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 GPT-4 better than o3 Mini for coding?

Neither model has a coding score yet, so the two cannot be ranked on coding. Pick GPT-4 for work measured by SWE-bench Verified or LMArena Text: coding, where it leads.

Which is cheaper, GPT-4 or o3 Mini?

GPT-4 costs $30.00 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, GPT-4 or o3 Mini?

o3 Mini, with 200K tokens against 8K.

How many benchmarks is the GPT-4 vs o3 Mini comparison based on?

37 benchmarks have a result for both models as of October 22, 2026. GPT-4'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