Enter opens the highlighted result. Esc closes.

GPT-5 vs GPT-5.4 Mini

GPT-5 leads GPT-5.4 Mini on coding, 38.8 to 35.8 on the Vibe Coding Index, and GPT-5.4 Mini costs 2.2x less per output token ($4.50 vs $10.00 per million). Updated October 22, 2026; 76 benchmarks have a result for both.

Replace GPT-5 Replace GPT-5.4 Mini
GPT-5OpenAI
Coding
38.8
Overall
51.5
Output $/M
$10.00
32
GPT-5.4 MiniOpenAI
Coding
35.8
Overall
44.0
Output $/M
$4.50
44
vs boards won of 76 shared

GPT-5 or GPT-5.4 Mini: which to pick

Pick GPT-5 for coding: it scores 38.8 on the Vibe Coding Index against 35.8 for GPT-5.4 Mini, though on 3 benchmarks against 5.

Pick GPT-5.4 Mini for output tokens 2.2x cheaper ($4.50 vs $10.00 per million) and work measured by AA Coding Index or SWE-bench Verified (Vals AI), where it leads.

Model AGPT-5OpenAI38.8/1003 independent benchmarks$0.39 per solved taskModel BGPT-5.4 MiniOpenAI35.8/1005 independent benchmarks$0.70 per solved task
Shared results
76
GPT-5 only
37
GPT-5.4 Mini only
13
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
GPT-5 38.8 from 3 benchmarks, GPT-5.4 Mini 35.8 from 5 benchmarks.
Widest category
Agentic work, 8.3 points apart on average over 2 shared benchmarks.
Widest single gap
Kagi LLM Benchmark: GPT-5 72.7% against GPT-5.4 Mini 37.9%, 34.8 points apart on a 0 to 100 scale.
Output price
GPT-5 $10.00 against GPT-5.4 Mini $4.50 per million output tokens, 2.2x apart.
Context window
Both take 400K 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
CategoryGPT-5BarsGPT-5.4 MiniTies
Coding47
Intelligence11
Agentic work20
Reasoning78
Math34
Knowledge82
General722
All shared boards3244
CodingLike-for-likeSix of these boards feed the Vibe Coding Index47
Coding benchmarks for GPT-5 and GPT-5.4 Mini
BenchmarkGPT-5GPT-5.4 MiniLeader
Aider polyglot88.0%Not measuredOnly GPT-5 measured
SWE-bench Verified74.4%Not measuredOnly GPT-5 measured
LMArena WebDev14181397GPT-5
AA Coding Index37.856.1GPT-5.4 Mini
LiveCodeBench (Vals AI)85.9%81.5%GPT-5
SWE-bench Verified (Vals AI)69.0%73.0%GPT-5.4 Mini
Terminal-Bench 4 (Vals AI)Not measured2.5%Only GPT-5.4 Mini measured
Vibe Code Bench (Vals AI)20.1%48.0%GPT-5.4 Mini
Code migration (Vals AI)Not measured12.9%Only GPT-5.4 Mini measured
ProgramBench (Vals AI)Not measured0.0%Only GPT-5.4 Mini measured
Terminal-Bench 2.1 (Vals AI)Not measured54.7%Only GPT-5.4 Mini measured
LiveCodeBench (Artificial Analysis run)84.6%Not measuredOnly GPT-5 measured
SciCodeNot measured52.1%Only GPT-5.4 Mini measured
Terminal-Bench Hard (Artificial Analysis run)37.9%52.3%GPT-5.4 Mini
Terminal-Bench49.6%Not measuredOnly GPT-5 measured
FrontierCodeNot measured27.0%Only GPT-5.4 Mini measured
GSO-Bench6.9%Not measuredOnly GPT-5 measured
WeirdML60.7%60.3%GPT-5
ALE-Bench807.61188.6GPT-5.4 Mini
LMArena Text: coding14361438GPT-5.4 Mini
LMArena Text: software and IT14201436GPT-5.4 Mini
LMArena WebDev: ReactNot measured1386Only GPT-5.4 Mini measured
LMArena WebDev: HTML14271419GPT-5
SciCode0.0%Not measuredOnly GPT-5 measured
Neither model has a result on the other 15 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index11
Intelligence benchmarks for GPT-5 and GPT-5.4 Mini
BenchmarkGPT-5GPT-5.4 MiniLeader
AA Intelligence Index23.024.1GPT-5.4 Mini
Epoch Capabilities Index150.0148.7GPT-5
Agentic workLike-for-likePublic boards, shown as published, kept out of the index20
Agentic work benchmarks for GPT-5 and GPT-5.4 Mini
BenchmarkGPT-5GPT-5.4 MiniLeader
AA Agentic IndexNot measured17.9Only GPT-5.4 Mini measured
Finance Agent (Vals AI)Not measured45.4%Only GPT-5.4 Mini measured
Tax Agent Bench (Vals AI)Not measured8.8%Only GPT-5.4 Mini measured
Legal Research Bench (Vals AI)Not measured12.5%Only GPT-5.4 Mini measured
Excel Modeling Benchmark (Vals AI)Not measured45.4%Only GPT-5.4 Mini measured
τ²-Bench Telecom86.5%83.3%GPT-5
METR time horizons69.6%Not measuredOnly GPT-5 measured
Remote Labor Index1.7%Not measuredOnly GPT-5 measured
GDPval34.8%Not measuredOnly GPT-5 measured
BALROG32.8%Not measuredOnly GPT-5 measured
DeepResearch Bench49.6%36.3%GPT-5
BrowseComp-Plus80.0%Not measuredOnly GPT-5 measured
Neither model has a result on the other 29 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index78
Reasoning benchmarks for GPT-5 and GPT-5.4 Mini
BenchmarkGPT-5GPT-5.4 MiniLeader
GPQA Diamond85.6%83.1%GPT-5
MMMU Pro (Vals AI)81.5%79.3%GPT-5
GPQA Diamond (Artificial Analysis run)85.4%87.5%GPT-5.4 Mini
Humanity's Last Exam (Artificial Analysis run)28.5%28.1%GPT-5
GPQA Diamond (Epoch AI run)86.2%86.9%GPT-5.4 Mini
ARC-AGI65.7%63.7%GPT-5
ARC-AGI-29.9%18.9%GPT-5.4 Mini
SimpleBench56.7%Not measuredOnly GPT-5 measured
Chess puzzles36.0%23.0%GPT-5
Mystery game puzzles23.0%11.0%GPT-5
EBR-bench12.7%Not measuredOnly GPT-5 measured
VPCT66.0%Not measuredOnly GPT-5 measured
LMArena Text: hard prompts14151424GPT-5.4 Mini
LMArena Text: expert14191435GPT-5.4 Mini
LMArena Text: hard prompts in English14191420GPT-5.4 Mini
LMArena Vision: diagrams12521266GPT-5.4 Mini
LMArena Vision: homework12781285GPT-5.4 Mini
Kagi LLM Benchmark72.7%37.9%GPT-5
Neither model has a result on the other 4 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index34
Math benchmarks for GPT-5 and GPT-5.4 Mini
BenchmarkGPT-5GPT-5.4 MiniLeader
AIME93.4%95.6%GPT-5.4 Mini
MATH 500 (Vals AI)96.0%Not measuredOnly GPT-5 measured
MGSM (Vals AI)92.8%Not measuredOnly GPT-5 measured
AA Math Index94.3Not measuredOnly GPT-5 measured
AIME 2025 (Artificial Analysis run)94.3%Not measuredOnly GPT-5 measured
OTIS Mock AIME91.4%88.9%GPT-5
FrontierMath, tiers 1 to 355.4%51.2%GPT-5
FrontierMath, tier 422.0%9.8%GPT-5
ProofBench18.0%21.0%GPT-5.4 Mini
MATH level 598.1%Not measuredOnly GPT-5 measured
LMArena Text: math14071418GPT-5.4 Mini
LMArena Text: mathematical work14051429GPT-5.4 Mini
Neither model has a result on the other 1 board here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index82
Knowledge benchmarks for GPT-5 and GPT-5.4 Mini
BenchmarkGPT-5GPT-5.4 MiniLeader
MMLU Pro86.5%84.5%GPT-5
LegalBench (Vals AI)86.0%Not measuredOnly GPT-5 measured
CaseLaw (Vals AI)66.5%51.7%GPT-5
CorpFin (Vals AI)61.1%60.9%GPT-5
TaxEval (Vals AI)73.4%71.2%GPT-5
MortgageTax (Vals AI)65.5%63.5%GPT-5
MedQA (Vals AI)96.3%Not measuredOnly GPT-5 measured
MedCode (Vals AI)49.6%Not measuredOnly GPT-5 measured
MMLU Pro (Artificial Analysis run)87.1%Not measuredOnly GPT-5 measured
SimpleQA Verified50.1%29.4%GPT-5
GeoBench81.0%Not measuredOnly GPT-5 measured
LMArena Text: science14161417GPT-5.4 Mini
LMArena Text: medicine and healthcare14131395GPT-5
LMArena Text: legal and government14311414GPT-5
LMArena Text: business and finance14001418GPT-5.4 Mini
FACTS Benchmark Suite56.5%Not measuredOnly GPT-5 measured
Neither model has a result on the other 2 boards here
Web designDirectional onlyPublic boards, shown as published, kept out of the index8 boards, none shared
Web design benchmarks for GPT-5 and GPT-5.4 Mini
BenchmarkGPT-5GPT-5.4 MiniLeader
Design Arena: websites1184Not measuredOnly GPT-5 measured
Design Arena: UI components1177Not measuredOnly GPT-5 measured
Design Arena: game dev1185Not measuredOnly GPT-5 measured
Design Arena: data viz1222Not measuredOnly GPT-5 measured
Design Arena: 3D1055Not measuredOnly GPT-5 measured
Design Arena: all code categories1167Not measuredOnly GPT-5 measured
Design Arena: SVG1188Not measuredOnly GPT-5 measured
Design Arena: ASCII art1141Not measuredOnly GPT-5 measured
Neither model has a result on the other 1 board here
GeneralLike-for-likePublic boards, shown as published, kept out of the index722
General benchmarks for GPT-5 and GPT-5.4 Mini
BenchmarkGPT-5GPT-5.4 MiniLeader
SAGE (Vals AI)43.7%50.8%GPT-5.4 Mini
MedScribe (Vals AI)83.7%Not measuredOnly GPT-5 measured
Vals Multimodal IndexNot measured54.2%Only GPT-5.4 Mini measured
IFBench73.1%73.3%GPT-5.4 Mini
Long context reasoning (AA-LCR)78.2%77.0%GPT-5
DTBench90.7%80.0%GPT-5
LMCA40.0%40.8%GPT-5.4 Mini
Fiction.LiveBench97.2%Not measuredOnly GPT-5 measured
Creative writing (Lech Mazur)86.0%Not measuredOnly GPT-5 measured
LMArena Text14061412GPT-5.4 Mini
LMArena Text: instruction following13881405GPT-5.4 Mini
LMArena Text: creative writing13651370GPT-5.4 Mini
LMArena Vision12321245GPT-5.4 Mini
LMArena Text: English14091412GPT-5.4 Mini
LMArena Text: non-English13971405GPT-5.4 Mini
LMArena Text: Chinese14221446GPT-5.4 Mini
LMArena Text: German14161408GPT-5
LMArena Text: Japanese14091375GPT-5
LMArena Text: Korean13601370GPT-5.4 Mini
LMArena Text: French14091441GPT-5.4 Mini
LMArena Text: Spanish13991405GPT-5.4 Mini
LMArena Text: Russian14071417GPT-5.4 Mini
LMArena Text: Polish14311415GPT-5
LMArena Text: multi-turn14261429GPT-5.4 Mini
LMArena Text: longer queries13991408GPT-5.4 Mini
LMArena Text: writing and language13841393GPT-5.4 Mini
LMArena Text: entertainment and media13791373GPT-5
LMArena Vision: English12311244GPT-5.4 Mini
LMArena Vision: Chinese12671286GPT-5.4 Mini
LMArena Vision: reading text12461253GPT-5.4 Mini
LMArena Vision: humor12191235GPT-5.4 Mini
LMArena Vision: captioning1212Not measuredOnly GPT-5 measured
LMArena Vision: recognizing things12631218GPT-5
LMArena Vision: creative writing12101222GPT-5.4 Mini
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 GPT-5 and GPT-5.4 Mini
BenchmarkGPT-5GPT-5.4 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-5$0.0063Fits in one request
GPT-5.4 Mini$0.0030Fits in one request

GPT-5.4 Mini costs less

Repository review

50K input + 3K output tokens

GPT-5$0.092Fits in one request
GPT-5.4 Mini$0.051Fits in one request

GPT-5.4 Mini costs less

Agent loop

200K input + 10K output tokens

GPT-5$0.350Fits in one request
GPT-5.4 Mini$0.195Fits in one request

GPT-5.4 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-5 and GPT-5.4 Mini
SpecificationOpenAI GPT-5OpenAI GPT-5.4 Mini
MakerOpenAIOpenAI
WeightsNo public weights listedNo public weights listed
ReleasedAugust 7, 2025March 17, 2026
Context window400K400K
Input $/Mtok$1.25$0.75
Output $/Mtok$10.00$4.50
Coding index38.835.8
Independent measurements behind it35
Cost per solved task$0.39$0.70
SourceOpenRouter listingOpenRouter listing

Questions

Is GPT-5 better than GPT-5.4 Mini for coding?

Pick GPT-5 for coding: it scores 38.8 on the Vibe Coding Index against 35.8 for GPT-5.4 Mini, though on 3 benchmarks against 5. Pick GPT-5.4 Mini for output tokens 2.2x cheaper ($4.50 vs $10.00 per million) and work measured by AA Coding Index or SWE-bench Verified (Vals AI), where it leads.

Which is cheaper, GPT-5 or GPT-5.4 Mini?

GPT-5 costs $1.25 per million input tokens and $10.00 per million output tokens; GPT-5.4 Mini costs $0.75 and $4.50. Per solved SWE-bench Verified task, GPT-5 costs $0.39 and GPT-5.4 Mini $0.70.

Which has the bigger context window, GPT-5 or GPT-5.4 Mini?

Neither: both take 400K tokens.

How many benchmarks is the GPT-5 vs GPT-5.4 Mini comparison based on?

76 benchmarks have a result for both models as of October 22, 2026. GPT-5's coding index rests on 3 independent benchmarks and GPT-5.4 Mini's on 5. Where only one model has a result, the page says so instead of naming a winner.

Compare next

Embed this comparison on your site

Free under CC BY 4.0, while the source link stays visible. Preview the frame · Terms and other embeds

<iframe src="https://llmbenchmark.ai/embed/compare/gpt-5-vs-gpt-5-4-mini" title="GPT-5 vs GPT-5.4 Mini, LLMBenchmark.ai" width="100%" height="360" style="border:0;max-width:100%" loading="lazy"></iframe>
<p style="font:13px/1.4 sans-serif;margin:6px 0 0">Source: <a href="https://llmbenchmark.ai/compare/gpt-5-vs-gpt-5-4-mini">LLMBenchmark.ai, GPT-5 vs GPT-5.4 Mini</a></p>