LLMBenchmark.ai

Enter opens the highlighted result. Esc closes.

GPT-4.1 vs GPT-5.4 Mini

Updated October 21, 2026. 65 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.

Replace GPT-4.1 Replace GPT-5.4 Mini
GPT-4.1OpenAI
Coding
46.5
Overall
12.7
Output $/M
$8.00
5
GPT-5.4 MiniOpenAI
Coding
28.2
Overall
24.1
Output $/M
$4.50
60
vs boards won of 65 shared

Decision reading

Pick GPT-4.1 for coding: it scores 46.5 on the Vibe Coding Index against 28.2 for GPT-5.4 Mini.

Pick GPT-5.4 Mini when output tokens cost 1.8x less, or when what matters is LiveCodeBench (Vals AI) or Terminal-Bench Hard (Artificial Analysis run), where it leads.

Model AGPT-4.1OpenAI46.5/1002 independent benchmarks$0.37 per solved taskModel BGPT-5.4 MiniOpenAI28.2/1001 independent benchmark$0.70 per solved task
Shared results
65
GPT-4.1 only
22
GPT-5.4 Mini only
23
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-4.1 46.5 from 2 benchmarks, GPT-5.4 Mini 28.2 from 1 benchmark.
Widest category
Agentic work, 36.3 points apart on average over 1 shared benchmark.
Widest single gap
ARC-AGI: GPT-4.1 5.5% against GPT-5.4 Mini 63.7%, 58.2 points apart on a 0 to 100 scale.
Output price
GPT-4.1 $8.00 against GPT-5.4 Mini $4.50 per million output tokens, 1.8x apart.
Context window
GPT-4.1 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-4.1BarsGPT-5.4 MiniTies
Coding06
Intelligence02
Agentic work01
Reasoning013
Math05
Knowledge55
General028
All shared boards560
CodingLike-for-likeFour of these boards feed the Vibe Coding Index06
Coding benchmarks for GPT-4.1 and GPT-5.4 Mini
BenchmarkGPT-4.1GPT-5.4 MiniLeader
Aider polyglot52.4%Not measuredOnly GPT-4.1 measured
SWE-bench Verified39.6%Not measuredOnly GPT-4.1 measured
SWE-bench Multimodal31.1%Not measuredOnly GPT-4.1 measured
LMArena WebDevNot measured1397Only GPT-5.4 Mini measured
AA Coding IndexNot measured56.1Only GPT-5.4 Mini measured
LiveCodeBench (Vals AI)54.7%81.5%GPT-5.4 Mini
SWE-bench Verified (Vals AI)Not measured73.0%Only GPT-5.4 Mini measured
Terminal-Bench 4 (Vals AI)Not measured2.5%Only GPT-5.4 Mini measured
Vibe Code Bench (Vals AI)Not measured48.0%Only GPT-5.4 Mini measured
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)45.7%Not measuredOnly GPT-4.1 measured
SciCodeNot measured52.1%Only GPT-5.4 Mini measured
Terminal-Bench Hard (Artificial Analysis run)13.6%52.3%GPT-5.4 Mini
FrontierCodeNot measured27.0%Only GPT-5.4 Mini measured
WeirdML39.0%60.3%GPT-5.4 Mini
ALE-Bench558.11188.6GPT-5.4 Mini
LMArena Text: coding13901438GPT-5.4 Mini
LMArena Text: software and IT13911436GPT-5.4 Mini
LMArena WebDev: ReactNot measured1386Only GPT-5.4 Mini measured
LMArena WebDev: HTMLNot measured1419Only GPT-5.4 Mini measured
Neither model has a result on the other 16 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
Intelligence benchmarks for GPT-4.1 and GPT-5.4 Mini
BenchmarkGPT-4.1GPT-5.4 MiniLeader
AA Intelligence Index12.724.1GPT-5.4 Mini
Epoch Capabilities Index136.7148.7GPT-5.4 Mini
Agentic workLike-for-likePublic boards, shown as published, kept out of the index01
Agentic work benchmarks for GPT-4.1 and GPT-5.4 Mini
BenchmarkGPT-4.1GPT-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 Telecom47.1%83.3%GPT-5.4 Mini
DeepResearch BenchNot measured36.3%Only GPT-5.4 Mini measured
Neither model has a result on the other 32 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index013
Reasoning benchmarks for GPT-4.1 and GPT-5.4 Mini
BenchmarkGPT-4.1GPT-5.4 MiniLeader
GPQA Diamond65.4%83.1%GPT-5.4 Mini
MMMU Pro (Vals AI)72.4%79.3%GPT-5.4 Mini
GPQA Diamond (Artificial Analysis run)66.6%87.5%GPT-5.4 Mini
Humanity's Last Exam (Artificial Analysis run)4.2%28.1%GPT-5.4 Mini
GPQA Diamond (Epoch AI run)66.9%86.9%GPT-5.4 Mini
ARC-AGI5.5%63.7%GPT-5.4 Mini
ARC-AGI-20.4%18.9%GPT-5.4 Mini
SimpleBench27.0%Not measuredOnly GPT-4.1 measured
Chess puzzles3.0%23.0%GPT-5.4 Mini
Mystery game puzzlesNot measured11.0%Only GPT-5.4 Mini measured
LMArena Text: hard prompts13841424GPT-5.4 Mini
LMArena Text: expert13641435GPT-5.4 Mini
LMArena Text: hard prompts in English13931420GPT-5.4 Mini
LMArena Vision: diagrams12151266GPT-5.4 Mini
LMArena Vision: homework12481285GPT-5.4 Mini
Neither model has a result on the other 6 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index05
Math benchmarks for GPT-4.1 and GPT-5.4 Mini
BenchmarkGPT-4.1GPT-5.4 MiniLeader
AIME39.6%95.6%GPT-5.4 Mini
MATH 500 (Vals AI)87.2%Not measuredOnly GPT-4.1 measured
MGSM (Vals AI)87.7%Not measuredOnly GPT-4.1 measured
AA Math Index34.7Not measuredOnly GPT-4.1 measured
AIME 2025 (Artificial Analysis run)34.7%Not measuredOnly GPT-4.1 measured
OTIS Mock AIME38.3%88.9%GPT-5.4 Mini
FrontierMath, tiers 1 to 36.0%51.2%GPT-5.4 Mini
FrontierMath, tier 4Not measured9.8%Only GPT-5.4 Mini measured
ProofBenchNot measured21.0%Only GPT-5.4 Mini measured
MATH level 583.0%Not measuredOnly GPT-4.1 measured
LMArena Text: math13691418GPT-5.4 Mini
LMArena Text: mathematical work13601429GPT-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 index55
Knowledge benchmarks for GPT-4.1 and GPT-5.4 Mini
BenchmarkGPT-4.1GPT-5.4 MiniLeader
MMLU Pro80.5%84.5%GPT-5.4 Mini
LegalBench (Vals AI)83.1%Not measuredOnly GPT-4.1 measured
CaseLaw (Vals AI)69.9%51.7%GPT-4.1
CorpFin (Vals AI)63.0%60.9%GPT-4.1
TaxEval (Vals AI)75.1%71.2%GPT-4.1
MortgageTax (Vals AI)65.9%63.5%GPT-4.1
MedQA (Vals AI)91.2%Not measuredOnly GPT-4.1 measured
MMLU Pro (Artificial Analysis run)80.6%Not measuredOnly GPT-4.1 measured
SimpleQA Verified31.1%29.4%GPT-4.1
GeoBench72.0%Not measuredOnly GPT-4.1 measured
LMArena Text: science13821417GPT-5.4 Mini
LMArena Text: medicine and healthcare13791395GPT-5.4 Mini
LMArena Text: legal and government13991414GPT-5.4 Mini
LMArena Text: business and finance13691418GPT-5.4 Mini
Neither model has a result on the other 3 boards here
Web designDirectional onlyPublic boards, shown as published, kept out of the index6 boards, none shared
Web design benchmarks for GPT-4.1 and GPT-5.4 Mini
BenchmarkGPT-4.1GPT-5.4 MiniLeader
Design Arena: websites1039Not measuredOnly GPT-4.1 measured
Design Arena: UI components1000Not measuredOnly GPT-4.1 measured
Design Arena: game dev1080Not measuredOnly GPT-4.1 measured
Design Arena: data viz1104Not measuredOnly GPT-4.1 measured
Design Arena: 3D850Not measuredOnly GPT-4.1 measured
Design Arena: all code categories1026Not measuredOnly GPT-4.1 measured
Neither model has a result on the other 3 boards here
GeneralLike-for-likePublic boards, shown as published, kept out of the index028
General benchmarks for GPT-4.1 and GPT-5.4 Mini
BenchmarkGPT-4.1GPT-5.4 MiniLeader
SAGE (Vals AI)Not measured50.8%Only GPT-5.4 Mini measured
Vals Multimodal IndexNot measured54.2%Only GPT-5.4 Mini measured
IFBench43.0%73.3%GPT-5.4 Mini
Long context reasoning (AA-LCR)68.3%77.0%GPT-5.4 Mini
DTBench68.3%80.0%GPT-5.4 Mini
LMCA25.6%40.8%GPT-5.4 Mini
Fiction.LiveBench63.9%Not measuredOnly GPT-4.1 measured
LMArena Text13831412GPT-5.4 Mini
LMArena Text: instruction following13671405GPT-5.4 Mini
LMArena Text: creative writing13631370GPT-5.4 Mini
LMArena Vision12101245GPT-5.4 Mini
LMArena Text: English13921412GPT-5.4 Mini
LMArena Text: non-English13701405GPT-5.4 Mini
LMArena Text: Chinese13821446GPT-5.4 Mini
LMArena Text: German13811408GPT-5.4 Mini
LMArena Text: Japanese13191375GPT-5.4 Mini
LMArena Text: Korean13381370GPT-5.4 Mini
LMArena Text: French13821441GPT-5.4 Mini
LMArena Text: Spanish13761405GPT-5.4 Mini
LMArena Text: Russian13771417GPT-5.4 Mini
LMArena Text: Polish13891415GPT-5.4 Mini
LMArena Text: multi-turn13971429GPT-5.4 Mini
LMArena Text: longer queries13851408GPT-5.4 Mini
LMArena Text: writing and language13711393GPT-5.4 Mini
LMArena Text: entertainment and media13651373GPT-5.4 Mini
LMArena Vision: English12091244GPT-5.4 Mini
LMArena Vision: Chinese12261286GPT-5.4 Mini
LMArena Vision: reading text12181253GPT-5.4 Mini
LMArena Vision: humor11961235GPT-5.4 Mini
LMArena Vision: captioning1207Not measuredOnly GPT-4.1 measured
LMArena Vision: recognizing things12081218GPT-5.4 Mini
LMArena Vision: creative writing12101222GPT-5.4 Mini
Neither model has a result on the other 14 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for GPT-4.1 and GPT-5.4 Mini
BenchmarkGPT-4.1GPT-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-4.1$0.0060Fits 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-4.1$0.124Fits 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-4.1$0.480Fits 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-4.1 and GPT-5.4 Mini
SpecificationOpenAI GPT-4.1OpenAI GPT-5.4 Mini
MakerOpenAIOpenAI
WeightsNo public weights listedNo public weights listed
ReleasedApril 14, 2025March 17, 2026
Context window1.05M400K
Input $/Mtok$2.00$0.75
Output $/Mtok$8.00$4.50
Coding index46.528.2
Independent measurements behind it21
Cost per solved task$0.37$0.70
SourceOpenRouter listingOpenRouter listing

Questions

Is GPT-4.1 better than GPT-5.4 Mini for coding?

Pick GPT-4.1 for coding: it scores 46.5 on the Vibe Coding Index against 28.2 for GPT-5.4 Mini. Pick GPT-5.4 Mini when output tokens cost 1.8x less, or when what matters is LiveCodeBench (Vals AI) or Terminal-Bench Hard (Artificial Analysis run), where it leads.

Which is cheaper, GPT-4.1 or GPT-5.4 Mini?

GPT-4.1 costs $2.00 per million input tokens and $8.00 per million output tokens; GPT-5.4 Mini costs $0.75 and $4.50. Per solved SWE-bench Verified task, GPT-4.1 costs $0.37 and GPT-5.4 Mini $0.70.

Which has the bigger context window, GPT-4.1 or GPT-5.4 Mini?

GPT-4.1, with 1.05M tokens against 400K.

How many benchmarks is the GPT-4.1 vs GPT-5.4 Mini comparison based on?

65 benchmarks have a result for both models as of October 21, 2026. GPT-4.1's coding index rests on 2 independent benchmarks 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