LLMBenchmark.ai

Enter opens the highlighted result. Esc closes.

GPT-4.1 Mini vs GPT-5 Mini

Updated October 21, 2026. 82 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 Mini Replace GPT-5 Mini
GPT-4.1 MiniOpenAI
Coding
28.5
Overall
10.2
Output $/M
$1.60
2
GPT-5 MiniOpenAI
Coding
59.8
Overall
20.6
Output $/M
$2.00
80
vs boards won of 82 shared

Decision reading

Pick GPT-5 Mini for coding: it scores 59.8 on the Vibe Coding Index against 28.5 for GPT-4.1 Mini, though on 1 benchmark against 2.

Pick GPT-4.1 Mini when output tokens cost 1.3x less, or when the context window is larger, 1.05M against 400K tokens.

Model AGPT-4.1 MiniOpenAI28.5/1002 independent benchmarks$1.818 per solved taskModel BGPT-5 MiniOpenAI59.8/1001 independent benchmark$0.08 per solved task
Shared results
82
GPT-4.1 Mini only
2
GPT-5 Mini only
16
Like-for-like categories
8 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 Mini 28.5 from 2 benchmarks, GPT-5 Mini 59.8 from 1 benchmark.
Widest category
Math, 24.6 points apart on average over 10 shared benchmarks.
Widest single gap
ARC-AGI: GPT-4.1 Mini 3.5% against GPT-5 Mini 54.3%, 50.8 points apart on a 0 to 100 scale.
Output price
GPT-4.1 Mini $1.60 against GPT-5 Mini $2.00 per million output tokens, 1.3x apart.
Context window
GPT-4.1 Mini takes 1.05M tokens, GPT-5 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-4.1 MiniBarsGPT-5 MiniTies
Coding07
Intelligence02
Agentic work01
Reasoning113
Math010
Knowledge012
Web design06
General129
All shared boards280
CodingLike-for-likeFour of these boards feed the Vibe Coding Index07
Coding benchmarks for GPT-4.1 Mini and GPT-5 Mini
BenchmarkGPT-4.1 MiniGPT-5 MiniLeader
Aider polyglot32.4%Not measuredOnly GPT-4.1 Mini measured
SWE-bench Verified23.9%59.8%GPT-5 Mini
SWE-bench MultilingualNot measured39.7%Only GPT-5 Mini measured
AA Coding Index20.2Not measuredOnly GPT-4.1 Mini measured
LiveCodeBench (Vals AI)58.2%86.6%GPT-5 Mini
SWE-bench Verified (Vals AI)Not measured60.8%Only GPT-5 Mini measured
Vibe Code Bench (Vals AI)Not measured14.2%Only GPT-5 Mini measured
LiveCodeBench (Artificial Analysis run)48.3%83.8%GPT-5 Mini
SciCodeNot measured39.0%Only GPT-5 Mini measured
Terminal-Bench Hard (Artificial Analysis run)7.6%33.3%GPT-5 Mini
Terminal-BenchNot measured34.8%Only GPT-5 Mini measured
WeirdML37.6%52.7%GPT-5 Mini
LMArena Text: coding13671406GPT-5 Mini
LMArena Text: software and IT13601394GPT-5 Mini
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-4.1 Mini and GPT-5 Mini
BenchmarkGPT-4.1 MiniGPT-5 MiniLeader
AA Intelligence Index10.220.6GPT-5 Mini
Epoch Capabilities Index134.9145.3GPT-5 Mini
Agentic workLike-for-likePublic boards, shown as published, kept out of the index01
Agentic work benchmarks for GPT-4.1 Mini and GPT-5 Mini
BenchmarkGPT-4.1 MiniGPT-5 MiniLeader
τ²-Bench Telecom52.9%71.1%GPT-5 Mini
Vending-Bench 2Not measured-$31Only GPT-5 Mini measured
Neither model has a result on the other 37 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index113
Reasoning benchmarks for GPT-4.1 Mini and GPT-5 Mini
BenchmarkGPT-4.1 MiniGPT-5 MiniLeader
GPQA Diamond67.9%80.3%GPT-5 Mini
MMMU Pro (Vals AI)70.5%78.9%GPT-5 Mini
GPQA Diamond (Artificial Analysis run)66.4%82.8%GPT-5 Mini
Humanity's Last Exam (Artificial Analysis run)5.0%21.5%GPT-5 Mini
GPQA Diamond (Epoch AI run)65.8%75.0%GPT-5 Mini
ARC-AGI3.5%54.3%GPT-5 Mini
ARC-AGI-20.0%4.4%GPT-5 Mini
Chess puzzles1.0%24.0%GPT-5 Mini
Mystery game puzzles7.0%10.0%GPT-5 Mini
VPCTNot measured40.2%Only GPT-5 Mini measured
LMArena Text: hard prompts13491380GPT-5 Mini
LMArena Text: expert13381379GPT-5 Mini
LMArena Text: hard prompts in English13621383GPT-5 Mini
LMArena Vision: diagrams11821202GPT-5 Mini
LMArena Vision: homework12141210GPT-4.1 Mini
Neither model has a result on the other 6 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index010
Math benchmarks for GPT-4.1 Mini and GPT-5 Mini
BenchmarkGPT-4.1 MiniGPT-5 MiniLeader
AIME49.4%91.5%GPT-5 Mini
MATH 500 (Vals AI)88.0%94.8%GPT-5 Mini
MGSM (Vals AI)87.8%92.6%GPT-5 Mini
AA Math Index46.390.7GPT-5 Mini
AIME 2025 (Artificial Analysis run)46.3%90.7%GPT-5 Mini
OTIS Mock AIME44.7%86.7%GPT-5 Mini
FrontierMath, tiers 1 to 36.7%46.7%GPT-5 Mini
FrontierMath, tier 4Not measured12.2%Only GPT-5 Mini measured
ProofBenchNot measured9.0%Only GPT-5 Mini measured
MATH level 587.3%97.8%GPT-5 Mini
LMArena Text: math13431378GPT-5 Mini
LMArena Text: mathematical work13471380GPT-5 Mini
Neither model has a result on the other 1 board here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index012
Knowledge benchmarks for GPT-4.1 Mini and GPT-5 Mini
BenchmarkGPT-4.1 MiniGPT-5 MiniLeader
MMLU Pro77.2%82.2%GPT-5 Mini
LegalBench (Vals AI)78.0%81.8%GPT-5 Mini
CaseLaw (Vals AI)Not measured68.5%Only GPT-5 Mini measured
CorpFin (Vals AI)57.9%60.2%GPT-5 Mini
TaxEval (Vals AI)71.9%75.2%GPT-5 Mini
MortgageTax (Vals AI)65.5%66.9%GPT-5 Mini
MedQA (Vals AI)84.6%96.1%GPT-5 Mini
MedCode (Vals AI)Not measured43.0%Only GPT-5 Mini measured
MMLU Pro (Artificial Analysis run)78.1%83.7%GPT-5 Mini
SimpleQA Verified12.7%21.6%GPT-5 Mini
LMArena Text: science13281371GPT-5 Mini
LMArena Text: medicine and healthcare13241380GPT-5 Mini
LMArena Text: legal and government13431375GPT-5 Mini
LMArena Text: business and finance13221358GPT-5 Mini
Neither model has a result on the other 3 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index06
Web design benchmarks for GPT-4.1 Mini and GPT-5 Mini
BenchmarkGPT-4.1 MiniGPT-5 MiniLeader
Design Arena: websites9971125GPT-5 Mini
Design Arena: UI components9611106GPT-5 Mini
Design Arena: game dev10711130GPT-5 Mini
Design Arena: data viz10341131GPT-5 Mini
Design Arena: 3D8371037GPT-5 Mini
Design Arena: all code categories9941115GPT-5 Mini
Design Arena: SVGNot measured1091Only GPT-5 Mini measured
Design Arena: ASCII artNot measured1124Only GPT-5 Mini measured
Neither model has a result on the other 1 board here
GeneralLike-for-likePublic boards, shown as published, kept out of the index129
General benchmarks for GPT-4.1 Mini and GPT-5 Mini
BenchmarkGPT-4.1 MiniGPT-5 MiniLeader
SAGE (Vals AI)Not measured43.0%Only GPT-5 Mini measured
MedScribe (Vals AI)Not measured80.6%Only GPT-5 Mini measured
IFBench38.3%75.4%GPT-5 Mini
Long context reasoning (AA-LCR)44.0%72.3%GPT-5 Mini
DTBench68.8%80.5%GPT-5 Mini
LMCA21.1%34.2%GPT-5 Mini
Fiction.LiveBench44.4%69.4%GPT-5 Mini
Creative writing (Lech Mazur)Not measured83.1%Only GPT-5 Mini measured
LMArena Text13411373GPT-5 Mini
LMArena Text: instruction following13331357GPT-5 Mini
LMArena Text: creative writing12991325GPT-5 Mini
LMArena Vision11811202GPT-5 Mini
LMArena Text: English13561379GPT-5 Mini
LMArena Text: non-English13181363GPT-5 Mini
LMArena Text: Chinese13291386GPT-5 Mini
LMArena Text: German13501366GPT-5 Mini
LMArena Text: Japanese12901341GPT-5 Mini
LMArena Text: Korean12981308GPT-5 Mini
LMArena Text: French13581386GPT-5 Mini
LMArena Text: Spanish13191354GPT-5 Mini
LMArena Text: Russian13241362GPT-5 Mini
LMArena Text: Polish13261378GPT-5 Mini
LMArena Text: multi-turn13541363GPT-5 Mini
LMArena Text: longer queries13441355GPT-5 Mini
LMArena Text: writing and language13191344GPT-5 Mini
LMArena Text: entertainment and media13001340GPT-5 Mini
LMArena Vision: English11911216GPT-5 Mini
LMArena Vision: Chinese11861214GPT-5 Mini
LMArena Vision: reading text11881199GPT-5 Mini
LMArena Vision: humor11821205GPT-5 Mini
LMArena Vision: captioning11741217GPT-5 Mini
LMArena Vision: recognizing things11871226GPT-5 Mini
LMArena Vision: creative writing11821181GPT-4.1 Mini
Neither model has a result on the other 13 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for GPT-4.1 Mini and GPT-5 Mini
BenchmarkGPT-4.1 MiniGPT-5 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 Mini$0.0012Fits in one request
GPT-5 Mini$0.0013Fits in one request

GPT-4.1 Mini costs less

Repository review

50K input + 3K output tokens

GPT-4.1 Mini$0.025Fits in one request
GPT-5 Mini$0.018Fits in one request

GPT-5 Mini costs less

Agent loop

200K input + 10K output tokens

GPT-4.1 Mini$0.096Fits in one request
GPT-5 Mini$0.070Fits in one request

GPT-5 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 Mini and GPT-5 Mini
SpecificationOpenAI GPT-4.1 MiniOpenAI GPT-5 Mini
MakerOpenAIOpenAI
WeightsNo public weights listedNo public weights listed
ReleasedApril 14, 2025August 7, 2025
Context window1.05M400K
Input $/Mtok$0.40$0.25
Output $/Mtok$1.60$2.00
Coding index28.559.8
Independent measurements behind it21
Cost per solved task$1.818$0.08
SourceOpenRouter listingOpenRouter listing

Questions

Is GPT-4.1 Mini better than GPT-5 Mini for coding?

Pick GPT-5 Mini for coding: it scores 59.8 on the Vibe Coding Index against 28.5 for GPT-4.1 Mini, though on 1 benchmark against 2. Pick GPT-4.1 Mini when output tokens cost 1.3x less, or when the context window is larger, 1.05M against 400K tokens.

Which is cheaper, GPT-4.1 Mini or GPT-5 Mini?

GPT-4.1 Mini costs $0.40 per million input tokens and $1.60 per million output tokens; GPT-5 Mini costs $0.25 and $2.00. Per solved SWE-bench Verified task, GPT-4.1 Mini costs $1.818 and GPT-5 Mini $0.08.

Which has the bigger context window, GPT-4.1 Mini or GPT-5 Mini?

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

How many benchmarks is the GPT-4.1 Mini vs GPT-5 Mini comparison based on?

82 benchmarks have a result for both models as of October 21, 2026. GPT-4.1 Mini's coding index rests on 2 independent benchmarks and GPT-5 Mini's on 1. Where only one model has a result, the page says so instead of naming a winner.

Compare next