LLMBenchmark.ai

Enter opens the highlighted result. Esc closes.

GPT-4 vs o4 Mini

Updated October 21, 2026. 36 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.

Replace GPT-4 Replace o4 Mini
GPT-4OpenAI
Coding
22.4
Overall
6.7
Output $/M
$60.00
0
o4 MiniOpenAI
Coding
68.6
Overall
16.7
Output $/M
$4.40
36
vs boards won of 36 shared

Decision reading

Pick o4 Mini for coding: it scores 68.6 on the Vibe Coding Index against 22.4 for GPT-4.

GPT-4 is neither cheaper nor larger in context, and leads no benchmark both models were measured on.

Model AGPT-4OpenAI22.4/1001 independent benchmarkNo cost per solved taskModel Bo4 MiniOpenAI68.6/1002 independent benchmarksNo cost per solved task
Shared results
36
GPT-4 only
9
o4 Mini only
58
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-4 22.4 from 1 benchmark, o4 Mini 68.6 from 2 benchmarks.
Widest category
Coding, 32.5 points apart on average over 3 shared benchmarks.
Widest single gap
GPQA Diamond (Artificial Analysis run): GPT-4 34.9% against o4 Mini 78.4%, 43.5 points apart on a 0 to 100 scale.
Output price
GPT-4 $60.00 against o4 Mini $4.40 per million output tokens, 13.6x apart.
Context window
GPT-4 takes 8K tokens, o4 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-4Barso4 MiniTies
Coding03
Intelligence02
Reasoning04
Math02
Knowledge05
General020
All shared boards036
CodingLike-for-likeFour of these boards feed the Vibe Coding Index03
Coding benchmarks for GPT-4 and o4 Mini
BenchmarkGPT-4o4 MiniLeader
Aider polyglotNot measured72.0%Only o4 Mini measured
SWE-bench Verified22.4%64.6%o4 Mini
SWE-bench Lite39.7%Not measuredOnly GPT-4 measured
SWE-bench (full test set)12.5%Not measuredOnly GPT-4 measured
SWE-bench MultimodalNot measured33.9%Only o4 Mini measured
AA Coding Index13.1Not measuredOnly GPT-4 measured
LiveCodeBench (Vals AI)Not measured82.2%Only o4 Mini measured
LiveCodeBench (Artificial Analysis run)Not measured85.9%Only o4 Mini measured
Terminal-Bench Hard (Artificial Analysis run)Not measured15.2%Only o4 Mini measured
GSO-BenchNot measured3.6%Only o4 Mini measured
WeirdMLNot measured52.6%Only o4 Mini measured
LMArena Text: coding12091368o4 Mini
LMArena Text: software and IT11951367o4 Mini
Neither model has a result on the other 25 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
Intelligence benchmarks for GPT-4 and o4 Mini
BenchmarkGPT-4o4 MiniLeader
AA Intelligence Index6.716.7o4 Mini
Epoch Capabilities Index125.7145.5o4 Mini
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index2 boards, none shared
Agentic work benchmarks for GPT-4 and o4 Mini
BenchmarkGPT-4o4 MiniLeader
τ²-Bench TelecomNot measured55.6%Only o4 Mini measured
METR time horizonsNot measured63.9%Only o4 Mini 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-4 and o4 Mini
BenchmarkGPT-4o4 MiniLeader
GPQA DiamondNot measured74.5%Only o4 Mini measured
MMMU Pro (Vals AI)Not measured79.7%Only o4 Mini measured
GPQA Diamond (Artificial Analysis run)34.9%78.4%o4 Mini
Humanity's Last Exam (Artificial Analysis run)Not measured16.5%Only o4 Mini measured
GPQA Diamond (Epoch AI run)Not measured79.6%Only o4 Mini measured
ARC-AGINot measured58.7%Only o4 Mini measured
ARC-AGI-2Not measured6.1%Only o4 Mini measured
SimpleBenchNot measured38.7%Only o4 Mini measured
Chess puzzlesNot measured22.0%Only o4 Mini measured
Mystery game puzzlesNot measured5.0%Only o4 Mini measured
VPCTNot measured57.5%Only o4 Mini measured
BIG-Bench Hard75.1%Not measuredOnly GPT-4 measured
LMArena Text: hard prompts12001351o4 Mini
LMArena Text: expert11491343o4 Mini
LMArena Text: hard prompts in English12091366o4 Mini
LMArena Vision: diagramsNot measured1197Only o4 Mini measured
LMArena Vision: homeworkNot measured1234Only o4 Mini measured
Neither model has a result on the other 4 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index02
Math benchmarks for GPT-4 and o4 Mini
BenchmarkGPT-4o4 MiniLeader
AIMENot measured83.7%Only o4 Mini measured
MATH 500 (Vals AI)Not measured94.2%Only o4 Mini measured
MGSM (Vals AI)Not measured93.4%Only o4 Mini measured
AA Math IndexNot measured90.7Only o4 Mini measured
AIME 2025 (Artificial Analysis run)Not measured90.7%Only o4 Mini measured
OTIS Mock AIMENot measured81.7%Only o4 Mini measured
FrontierMath, tiers 1 to 3Not measured36.1%Only o4 Mini measured
FrontierMath, tier 4Not measured4.9%Only o4 Mini measured
MATH level 5Not measured97.8%Only o4 Mini measured
GSM8K92.0%Not measuredOnly GPT-4 measured
LMArena Text: math12301389o4 Mini
LMArena Text: mathematical work12281379o4 Mini
Neither model has a result on the other 1 board here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index05
Knowledge benchmarks for GPT-4 and o4 Mini
BenchmarkGPT-4o4 MiniLeader
MMLU ProNot measured80.6%Only o4 Mini measured
LegalBench (Vals AI)Not measured79.2%Only o4 Mini measured
CorpFin (Vals AI)Not measured59.0%Only o4 Mini measured
TaxEval (Vals AI)Not measured74.8%Only o4 Mini measured
MortgageTax (Vals AI)Not measured64.8%Only o4 Mini measured
MedQA (Vals AI)Not measured96.0%Only o4 Mini measured
MedCode (Vals AI)Not measured33.8%Only o4 Mini measured
MMLU Pro (Artificial Analysis run)56.2%83.2%o4 Mini
SimpleQA VerifiedNot measured19.6%Only o4 Mini measured
MMLU86.4%Not measuredOnly GPT-4 measured
GeoBenchNot measured64.0%Only o4 Mini measured
AI2 Reasoning Challenge96.3%Not measuredOnly GPT-4 measured
LMArena Text: science11771354o4 Mini
LMArena Text: medicine and healthcare11451361o4 Mini
LMArena Text: legal and government11911350o4 Mini
LMArena Text: business and finance11451325o4 Mini
Neither model has a result on the other 1 board here
Web designDirectional onlyPublic boards, shown as published, kept out of the index6 boards, none shared
Web design benchmarks for GPT-4 and o4 Mini
BenchmarkGPT-4o4 MiniLeader
Design Arena: websitesNot measured985Only o4 Mini measured
Design Arena: UI componentsNot measured983Only o4 Mini measured
Design Arena: game devNot measured1004Only o4 Mini measured
Design Arena: data vizNot measured990Only o4 Mini measured
Design Arena: 3DNot measured854Only o4 Mini measured
Design Arena: all code categoriesNot measured977Only o4 Mini measured
Neither model has a result on the other 3 boards here
GeneralLike-for-likePublic boards, shown as published, kept out of the index020
General benchmarks for GPT-4 and o4 Mini
BenchmarkGPT-4o4 MiniLeader
SAGE (Vals AI)Not measured41.1%Only o4 Mini measured
MedScribe (Vals AI)Not measured69.1%Only o4 Mini measured
IFBench33.2%68.7%o4 Mini
Long context reasoning (AA-LCR)Not measured61.0%Only o4 Mini measured
DTBench62.7%77.6%o4 Mini
LMCA17.1%26.5%o4 Mini
Fiction.LiveBenchNot measured77.8%Only o4 Mini measured
Creative writing (Lech Mazur)Not measured75.0%Only o4 Mini measured
HellaSwag95.3%Not measuredOnly GPT-4 measured
WinoGrande87.5%Not measuredOnly GPT-4 measured
LMArena Text12061353o4 Mini
LMArena Text: instruction following12011320o4 Mini
LMArena Text: creative writing11911294o4 Mini
LMArena VisionNot measured1194Only o4 Mini measured
LMArena Text: English12201367o4 Mini
LMArena Text: non-English11941337o4 Mini
LMArena Text: Chinese11841354o4 Mini
LMArena Text: German11981336o4 Mini
LMArena Text: Japanese11371308o4 Mini
LMArena Text: Korean10871312o4 Mini
LMArena Text: French12201364o4 Mini
LMArena Text: Spanish11971346o4 Mini
LMArena Text: Russian11951334o4 Mini
LMArena Text: Polish12651358o4 Mini
LMArena Text: multi-turn12061350o4 Mini
LMArena Text: longer queries11901315o4 Mini
LMArena Text: writing and language12191316o4 Mini
LMArena Text: entertainment and media11841308o4 Mini
LMArena Vision: EnglishNot measured1200Only o4 Mini measured
LMArena Vision: ChineseNot measured1218Only o4 Mini measured
LMArena Vision: reading textNot measured1197Only o4 Mini measured
LMArena Vision: humorNot measured1199Only o4 Mini measured
LMArena Vision: captioningNot measured1204Only o4 Mini measured
LMArena Vision: recognizing thingsNot measured1218Only o4 Mini measured
LMArena Vision: creative writingNot measured1166Only o4 Mini measured
Neither model has a result on the other 11 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for GPT-4 and o4 Mini
BenchmarkGPT-4o4 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
o4 Mini$0.0033Fits in one request

o4 Mini costs less

Repository review

50K input + 3K output tokens

GPT-4$1.68Exceeds the context window
o4 Mini$0.068Fits in one request

o4 Mini costs less

Agent loop

200K input + 10K output tokens

GPT-4$6.60Exceeds the context window
o4 Mini$0.264Exceeds the context window

o4 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 o4 Mini
SpecificationOpenAI GPT-4OpenAI o4 Mini
MakerOpenAIOpenAI
WeightsNo public weights listedNo public weights listed
ReleasedMay 28, 2023April 16, 2025
Context window8K200K
Input $/Mtok$30.00$1.10
Output $/Mtok$60.00$4.40
Coding index22.468.6
Independent measurements behind it12
Cost per solved taskNot computableNot computable
SourceOpenRouter listingOpenRouter listing

Questions

Is GPT-4 better than o4 Mini for coding?

Pick o4 Mini for coding: it scores 68.6 on the Vibe Coding Index against 22.4 for GPT-4. GPT-4 is neither cheaper nor larger in context, and leads no benchmark both models were measured on.

Which is cheaper, GPT-4 or o4 Mini?

GPT-4 costs $30.00 per million input tokens and $60.00 per million output tokens; o4 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 o4 Mini?

o4 Mini, with 200K tokens against 8K.

How many benchmarks is the GPT-4 vs o4 Mini comparison based on?

36 benchmarks have a result for both models as of October 21, 2026. GPT-4's coding index rests on 1 independent benchmark and o4 Mini's on 2. Where only one model has a result, the page says so instead of naming a winner.

Compare next