LLMBenchmark.ai

Enter opens the highlighted result. Esc closes.

GPT-5.4 vs GPT-5.4 Mini

Updated October 21, 2026. 78 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.

Replace GPT-5.4 Replace GPT-5.4 Mini
GPT-5.4OpenAI
Coding
37.7
Overall
39.0
Output $/M
$15.00
76
GPT-5.4 MiniOpenAI
Coding
28.2
Overall
24.1
Output $/M
$4.50
2
vs boards won of 78 shared

Decision reading

Pick GPT-5.4 for coding: it scores 37.7 on the Vibe Coding Index against 28.2 for GPT-5.4 Mini.

Pick GPT-5.4 Mini when output tokens cost 3.3x less, or when a solved task costs $0.70 against $1.02.

Model AGPT-5.4OpenAI37.7/1001 independent benchmark$1.02 per solved taskModel BGPT-5.4 MiniOpenAI28.2/1001 independent benchmark$0.70 per solved task
Shared results
78
GPT-5.4 only
31
GPT-5.4 Mini only
10
Like-for-like categories
7 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-5.4 37.7 from 1 benchmark, GPT-5.4 Mini 28.2 from 1 benchmark.
Widest category
Math, 19.2 points apart on average over 7 shared benchmarks.
Widest single gap
ARC-AGI-2: GPT-5.4 74.0% against GPT-5.4 Mini 18.9%, 55.1 points apart on a 0 to 100 scale.
Output price
GPT-5.4 $15.00 against GPT-5.4 Mini $4.50 per million output tokens, 3.3x apart.
Context window
GPT-5.4 takes 1.05M tokens, GPT-5.4 Mini 400K.

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-5.4BarsGPT-5.4 MiniTies
Coding140
Intelligence20
Agentic work11
Reasoning140
Math70
Knowledge100
General281
All shared boards762
CodingLike-for-likeFour of these boards feed the Vibe Coding Index140
Coding benchmarks for GPT-5.4 and GPT-5.4 Mini
BenchmarkGPT-5.4GPT-5.4 MiniLeader
LMArena WebDev14641397GPT-5.4
AA Coding Index71.156.1GPT-5.4
LiveCodeBench (Vals AI)84.1%81.5%GPT-5.4
SWE-bench Verified (Vals AI)78.2%73.0%GPT-5.4
Terminal-Bench 4 (Vals AI)Not measured2.5%Only GPT-5.4 Mini measured
Vibe Code Bench (Vals AI)67.4%48.0%GPT-5.4
Code migration (Vals AI)35.0%12.9%GPT-5.4
ProgramBench (Vals AI)0.5%0.0%GPT-5.4
Terminal-Bench 2.1 (Vals AI)Not measured54.7%Only GPT-5.4 Mini measured
SkillsBench (Vals AI)51.7%Not measuredOnly GPT-5.4 measured
SciCodeNot measured52.1%Only GPT-5.4 Mini measured
Terminal-Bench Hard (Artificial Analysis run)57.6%52.3%GPT-5.4
Terminal-Bench81.8%Not measuredOnly GPT-5.4 measured
FrontierCodeNot measured27.0%Only GPT-5.4 Mini measured
GSO-Bench31.4%Not measuredOnly GPT-5.4 measured
WeirdML77.7%60.3%GPT-5.4
MirrorCode15.6%Not measuredOnly GPT-5.4 measured
ALE-Bench1607.01188.6GPT-5.4
LMArena Text: coding14961438GPT-5.4
LMArena Text: software and IT14911436GPT-5.4
LMArena WebDev: React14541386GPT-5.4
LMArena WebDev: HTML14781419GPT-5.4
LMArena WebDev: from an image1436Not measuredOnly GPT-5.4 measured
Neither model has a result on the other 15 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
Intelligence benchmarks for GPT-5.4 and GPT-5.4 Mini
BenchmarkGPT-5.4GPT-5.4 MiniLeader
AA Intelligence Index39.024.1GPT-5.4
Epoch Capabilities Index157.3148.7GPT-5.4
Agentic workLike-for-likePublic boards, shown as published, kept out of the index11
Agentic work benchmarks for GPT-5.4 and GPT-5.4 Mini
BenchmarkGPT-5.4GPT-5.4 MiniLeader
AA Agentic IndexNot measured17.9Only GPT-5.4 Mini measured
Design Arena: agents building web apps1059Not measuredOnly GPT-5.4 measured
Design Arena: agents building full-stack apps1017Not measuredOnly GPT-5.4 measured
Design Arena: agents building mobile apps1087Not measuredOnly GPT-5.4 measured
Design Arena: agents building Android apps1037Not measuredOnly GPT-5.4 measured
Design Arena: agents building Godot games1135Not measuredOnly GPT-5.4 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 Telecom87.1%83.3%GPT-5.4
APEX-Agents52.4%Not measuredOnly GPT-5.4 measured
METR time horizons74.3%Not measuredOnly GPT-5.4 measured
DeepResearch Bench35.1%36.3%GPT-5.4 Mini
PostTrainBench19.0%Not measuredOnly GPT-5.4 measured
Vending-Bench 2$6,144Not measuredOnly GPT-5.4 measured
Neither model has a result on the other 23 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index140
Reasoning benchmarks for GPT-5.4 and GPT-5.4 Mini
BenchmarkGPT-5.4GPT-5.4 MiniLeader
GPQA Diamond91.7%83.1%GPT-5.4
MMMU Pro (Vals AI)87.5%79.3%GPT-5.4
GPQA Diamond (Artificial Analysis run)92.0%87.5%GPT-5.4
Humanity's Last Exam (Artificial Analysis run)43.7%28.1%GPT-5.4
GPQA Diamond (Epoch AI run)93.3%86.9%GPT-5.4
ARC-AGI93.7%63.7%GPT-5.4
ARC-AGI-274.0%18.9%GPT-5.4
Chess puzzles48.0%23.0%GPT-5.4
Mystery game puzzles37.0%11.0%GPT-5.4
EBR-bench25.4%Not measuredOnly GPT-5.4 measured
LMArena Text: hard prompts14851424GPT-5.4
LMArena Text: expert15071435GPT-5.4
LMArena Text: hard prompts in English14791420GPT-5.4
LMArena Vision: diagrams13271266GPT-5.4
LMArena Vision: homework13361285GPT-5.4
Neither model has a result on the other 6 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index70
Math benchmarks for GPT-5.4 and GPT-5.4 Mini
BenchmarkGPT-5.4GPT-5.4 MiniLeader
AIME96.7%95.6%GPT-5.4
OTIS Mock AIME97.8%88.9%GPT-5.4
FrontierMath, tiers 1 to 378.6%51.2%GPT-5.4
FrontierMath, tier 449.0%9.8%GPT-5.4
ProofBench56.0%21.0%GPT-5.4
LMArena Text: math14881418GPT-5.4
LMArena Text: mathematical work14971429GPT-5.4
Neither model has a result on the other 6 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index100
Knowledge benchmarks for GPT-5.4 and GPT-5.4 Mini
BenchmarkGPT-5.4GPT-5.4 MiniLeader
MMLU Pro87.5%84.5%GPT-5.4
LegalBench (Vals AI)86.0%Not measuredOnly GPT-5.4 measured
CaseLaw (Vals AI)63.8%51.7%GPT-5.4
CorpFin (Vals AI)65.3%60.9%GPT-5.4
TaxEval (Vals AI)74.0%71.2%GPT-5.4
MortgageTax (Vals AI)68.3%63.5%GPT-5.4
MedQA (Vals AI)96.1%Not measuredOnly GPT-5.4 measured
MedCode (Vals AI)41.3%Not measuredOnly GPT-5.4 measured
SimpleQA Verified45.1%29.4%GPT-5.4
LMArena Text: science14791417GPT-5.4
LMArena Text: medicine and healthcare14581395GPT-5.4
LMArena Text: legal and government14861414GPT-5.4
LMArena Text: business and finance14741418GPT-5.4
Neither model has a result on the other 4 boards here
Web designDirectional onlyPublic boards, shown as published, kept out of the index8 boards, none shared
Web design benchmarks for GPT-5.4 and GPT-5.4 Mini
BenchmarkGPT-5.4GPT-5.4 MiniLeader
Design Arena: websites1199Not measuredOnly GPT-5.4 measured
Design Arena: UI components1215Not measuredOnly GPT-5.4 measured
Design Arena: game dev1195Not measuredOnly GPT-5.4 measured
Design Arena: data viz1196Not measuredOnly GPT-5.4 measured
Design Arena: 3D1065Not measuredOnly GPT-5.4 measured
Design Arena: all code categories1180Not measuredOnly GPT-5.4 measured
Design Arena: SVG1141Not measuredOnly GPT-5.4 measured
Design Arena: ASCII art1188Not measuredOnly GPT-5.4 measured
Neither model has a result on the other 1 board here
GeneralLike-for-likePublic boards, shown as published, kept out of the index281
General benchmarks for GPT-5.4 and GPT-5.4 Mini
BenchmarkGPT-5.4GPT-5.4 MiniLeader
SAGE (Vals AI)43.3%50.8%GPT-5.4 Mini
MedScribe (Vals AI)77.5%Not measuredOnly GPT-5.4 measured
Vals Multimodal IndexNot measured54.2%Only GPT-5.4 Mini measured
IFBench73.9%73.3%GPT-5.4
Long context reasoning (AA-LCR)82.0%77.0%GPT-5.4
DTBench94.4%80.0%GPT-5.4
LMCA52.0%40.8%GPT-5.4
CL-bench27.9%Not measuredOnly GPT-5.4 measured
Furniture assembly37.5%Not measuredOnly GPT-5.4 measured
CL-bench Life21.7%Not measuredOnly GPT-5.4 measured
LMArena Text14691412GPT-5.4
LMArena Text: instruction following14691405GPT-5.4
LMArena Text: creative writing14391370GPT-5.4
LMArena Vision13031245GPT-5.4
LMArena Text: English14671412GPT-5.4
LMArena Text: non-English14651405GPT-5.4
LMArena Text: Chinese15201446GPT-5.4
LMArena Text: German14721408GPT-5.4
LMArena Text: Japanese14851375GPT-5.4
LMArena Text: Korean14491370GPT-5.4
LMArena Text: French14931441GPT-5.4
LMArena Text: Spanish14521405GPT-5.4
LMArena Text: Russian14801417GPT-5.4
LMArena Text: Polish14721415GPT-5.4
LMArena Text: multi-turn14821429GPT-5.4
LMArena Text: longer queries14731408GPT-5.4
LMArena Text: writing and language14581393GPT-5.4
LMArena Text: entertainment and media14381373GPT-5.4
LMArena Vision: English13011244GPT-5.4
LMArena Vision: Chinese13541286GPT-5.4
LMArena Vision: reading text13121253GPT-5.4
LMArena Vision: humor12841235GPT-5.4
LMArena Vision: recognizing things12511218GPT-5.4
LMArena Vision: creative writing12831222GPT-5.4
LMArena Document1471Not measuredOnly GPT-5.4 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-5.4 and GPT-5.4 Mini
BenchmarkGPT-5.4GPT-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-5.4$0.010Fits 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-5.4$0.170Fits 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-5.4$0.650Fits 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-5.4 and GPT-5.4 Mini
SpecificationOpenAI GPT-5.4OpenAI GPT-5.4 Mini
MakerOpenAIOpenAI
WeightsNo public weights listedNo public weights listed
ReleasedMarch 5, 2026March 17, 2026
Context window1.05M400K
Input $/Mtok$2.50$0.75
Output $/Mtok$15.00$4.50
Coding index37.728.2
Independent measurements behind it11
Cost per solved task$1.02$0.70
SourceOpenRouter listingOpenRouter listing

Questions

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

Pick GPT-5.4 for coding: it scores 37.7 on the Vibe Coding Index against 28.2 for GPT-5.4 Mini. Pick GPT-5.4 Mini when output tokens cost 3.3x less, or when a solved task costs $0.70 against $1.02.

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

GPT-5.4 costs $2.50 per million input tokens and $15.00 per million output tokens; GPT-5.4 Mini costs $0.75 and $4.50. Per solved SWE-bench Verified task, GPT-5.4 costs $1.02 and GPT-5.4 Mini $0.70.

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

GPT-5.4, with 1.05M tokens against 400K.

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

78 benchmarks have a result for both models as of October 21, 2026. GPT-5.4's coding index rests on 1 independent benchmark and GPT-5.4 Mini's on 1. Where only one model has a result, the page says so instead of naming a winner.

Compare next