Enter opens the highlighted result. Esc closes.

GPT-4.1 Mini vs GPT-5.2

Updated October 21, 2026. 79 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-5.2
GPT-4.1 MiniOpenAI
Coding
28.5
Overall
10.2
Output $/M
$1.60
0
GPT-5.2OpenAI
Coding
58.9
Overall
30.4
Output $/M
$14.00
79
vs boards won of 79 shared

Decision reading

Pick GPT-5.2 for coding: it scores 58.9 on the Vibe Coding Index against 28.5 for GPT-4.1 Mini.

Pick GPT-4.1 Mini when output tokens cost 8.8x less, or when a solved task costs $1.818 against $1.91.

Model AGPT-4.1 MiniOpenAI28.5/1002 independent benchmarks$1.818 per solved taskModel BGPT-5.2OpenAI58.9/1002 independent benchmarks$1.91 per solved task
Shared results
79
GPT-4.1 Mini only
5
GPT-5.2 only
32
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-5.2 58.9 from 2 benchmarks.
Widest category
Math, 37.9 points apart on average over 8 shared benchmarks.
Widest single gap
ARC-AGI: GPT-4.1 Mini 3.5% against GPT-5.2 86.2%, 82.7 points apart on a 0 to 100 scale.
Output price
GPT-4.1 Mini $1.60 against GPT-5.2 $14.00 per million output tokens, 8.8x apart.
Context window
GPT-4.1 Mini takes 1.05M tokens, GPT-5.2 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-5.2Ties
Coding07
Intelligence02
Agentic work01
Reasoning014
Math08
Knowledge012
Web design06
General029
All shared boards079
CodingLike-for-likeFour of these boards feed the Vibe Coding Index07
Coding benchmarks for GPT-4.1 Mini and GPT-5.2
BenchmarkGPT-4.1 MiniGPT-5.2Leader
Aider polyglot32.4%Not measuredOnly GPT-4.1 Mini measured
SWE-bench Verified23.9%72.8%GPT-5.2
SWE-bench MultilingualNot measured66.7%Only GPT-5.2 measured
LMArena WebDevNot measured1417Only GPT-5.2 measured
AA Coding Index20.2Not measuredOnly GPT-4.1 Mini measured
LiveCodeBench (Vals AI)58.2%85.4%GPT-5.2
SWE-bench Verified (Vals AI)Not measured75.8%Only GPT-5.2 measured
Vibe Code Bench (Vals AI)Not measured53.5%Only GPT-5.2 measured
LiveCodeBench (Artificial Analysis run)48.3%89.4%GPT-5.2
Terminal-Bench Hard (Artificial Analysis run)7.6%47.0%GPT-5.2
Terminal-BenchNot measured64.9%Only GPT-5.2 measured
GSO-BenchNot measured27.5%Only GPT-5.2 measured
WeirdML37.6%72.2%GPT-5.2
ALE-BenchNot measured1293.5Only GPT-5.2 measured
LMArena Text: coding13671442GPT-5.2
LMArena Text: software and IT13601434GPT-5.2
LMArena WebDev: HTMLNot measured1427Only GPT-5.2 measured
Neither model has a result on the other 21 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
Intelligence benchmarks for GPT-4.1 Mini and GPT-5.2
BenchmarkGPT-4.1 MiniGPT-5.2Leader
AA Intelligence Index10.230.4GPT-5.2
Epoch Capabilities Index134.9153.7GPT-5.2
Agentic workLike-for-likePublic boards, shown as published, kept out of the index01
Agentic work benchmarks for GPT-4.1 Mini and GPT-5.2
BenchmarkGPT-4.1 MiniGPT-5.2Leader
Design Arena: agents building web appsNot measured1086Only GPT-5.2 measured
Design Arena: agents building full-stack appsNot measured1043Only GPT-5.2 measured
Design Arena: agents building mobile appsNot measured1094Only GPT-5.2 measured
Design Arena: agents building Android appsNot measured1064Only GPT-5.2 measured
Design Arena: agents building Godot gamesNot measured1142Only GPT-5.2 measured
τ²-Bench Telecom52.9%84.8%GPT-5.2
METR time horizonsNot measured75.3%Only GPT-5.2 measured
Remote Labor IndexNot measured2.5%Only GPT-5.2 measured
GDPvalNot measured49.7%Only GPT-5.2 measured
DeepResearch BenchNot measured41.1%Only GPT-5.2 measured
Vending-Bench 2Not measured$3,591Only GPT-5.2 measured
Neither model has a result on the other 28 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index014
Reasoning benchmarks for GPT-4.1 Mini and GPT-5.2
BenchmarkGPT-4.1 MiniGPT-5.2Leader
GPQA Diamond67.9%91.7%GPT-5.2
MMMU Pro (Vals AI)70.5%86.7%GPT-5.2
GPQA Diamond (Artificial Analysis run)66.4%90.3%GPT-5.2
Humanity's Last Exam (Artificial Analysis run)5.0%37.7%GPT-5.2
GPQA Diamond (Epoch AI run)65.8%91.4%GPT-5.2
ARC-AGI3.5%86.2%GPT-5.2
ARC-AGI-20.0%52.9%GPT-5.2
SimpleBenchNot measured45.8%Only GPT-5.2 measured
Chess puzzles1.0%48.0%GPT-5.2
Mystery game puzzles7.0%23.0%GPT-5.2
EBR-benchNot measured23.0%Only GPT-5.2 measured
VPCTNot measured84.0%Only GPT-5.2 measured
LMArena Text: hard prompts13491428GPT-5.2
LMArena Text: expert13381445GPT-5.2
LMArena Text: hard prompts in English13621431GPT-5.2
LMArena Vision: diagrams11821265GPT-5.2
LMArena Vision: homework12141276GPT-5.2
Neither model has a result on the other 4 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index08
Math benchmarks for GPT-4.1 Mini and GPT-5.2
BenchmarkGPT-4.1 MiniGPT-5.2Leader
AIME49.4%96.9%GPT-5.2
MATH 500 (Vals AI)88.0%Not measuredOnly GPT-4.1 Mini measured
MGSM (Vals AI)87.8%94.0%GPT-5.2
AA Math Index46.399.0GPT-5.2
AIME 2025 (Artificial Analysis run)46.3%99.0%GPT-5.2
OTIS Mock AIME44.7%96.1%GPT-5.2
FrontierMath, tiers 1 to 36.7%67.4%GPT-5.2
FrontierMath, tier 4Not measured31.7%Only GPT-5.2 measured
ProofBenchNot measured15.0%Only GPT-5.2 measured
MATH level 587.3%Not measuredOnly GPT-4.1 Mini measured
LMArena Text: math13431440GPT-5.2
LMArena Text: mathematical work13471442GPT-5.2
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-5.2
BenchmarkGPT-4.1 MiniGPT-5.2Leader
MMLU Pro77.2%86.2%GPT-5.2
LegalBench (Vals AI)78.0%82.8%GPT-5.2
CaseLaw (Vals AI)Not measured66.0%Only GPT-5.2 measured
CorpFin (Vals AI)57.9%65.9%GPT-5.2
TaxEval (Vals AI)71.9%75.8%GPT-5.2
MortgageTax (Vals AI)65.5%67.1%GPT-5.2
MedQA (Vals AI)84.6%94.1%GPT-5.2
MedCode (Vals AI)Not measured49.8%Only GPT-5.2 measured
MMLU Pro (Artificial Analysis run)78.1%87.4%GPT-5.2
SimpleQA Verified12.7%37.1%GPT-5.2
LMArena Text: science13281425GPT-5.2
LMArena Text: medicine and healthcare13241425GPT-5.2
LMArena Text: legal and government13431427GPT-5.2
LMArena Text: business and finance13221414GPT-5.2
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-5.2
BenchmarkGPT-4.1 MiniGPT-5.2Leader
Design Arena: websites9971196GPT-5.2
Design Arena: UI components9611190GPT-5.2
Design Arena: game dev10711196GPT-5.2
Design Arena: data viz10341202GPT-5.2
Design Arena: 3D8371079GPT-5.2
Design Arena: all code categories9941171GPT-5.2
Design Arena: SVGNot measured1137Only GPT-5.2 measured
Design Arena: ASCII artNot measured1153Only GPT-5.2 measured
Neither model has a result on the other 1 board here
GeneralLike-for-likePublic boards, shown as published, kept out of the index029
General benchmarks for GPT-4.1 Mini and GPT-5.2
BenchmarkGPT-4.1 MiniGPT-5.2Leader
SAGE (Vals AI)Not measured49.3%Only GPT-5.2 measured
MedScribe (Vals AI)Not measured84.4%Only GPT-5.2 measured
IFBench38.3%75.4%GPT-5.2
Long context reasoning (AA-LCR)44.0%82.7%GPT-5.2
DTBench68.8%90.9%GPT-5.2
LMCA21.1%43.9%GPT-5.2
Fiction.LiveBench44.4%Not measuredOnly GPT-4.1 Mini measured
CL-benchNot measured18.2%Only GPT-5.2 measured
Furniture assemblyNot measured38.3%Only GPT-5.2 measured
LMArena Text13411416GPT-5.2
LMArena Text: instruction following13331409GPT-5.2
LMArena Text: creative writing12991376GPT-5.2
LMArena Vision11811246GPT-5.2
LMArena Text: English13561422GPT-5.2
LMArena Text: non-English13181405GPT-5.2
LMArena Text: Chinese13291447GPT-5.2
LMArena Text: German13501444GPT-5.2
LMArena Text: Japanese12901420GPT-5.2
LMArena Text: Korean12981374GPT-5.2
LMArena Text: French13581454GPT-5.2
LMArena Text: Spanish13191413GPT-5.2
LMArena Text: Russian13241415GPT-5.2
LMArena Text: Polish13261426GPT-5.2
LMArena Text: multi-turn13541419GPT-5.2
LMArena Text: longer queries13441413GPT-5.2
LMArena Text: writing and language13191392GPT-5.2
LMArena Text: entertainment and media13001378GPT-5.2
LMArena Vision: English11911243GPT-5.2
LMArena Vision: Chinese11861305GPT-5.2
LMArena Vision: reading text11881257GPT-5.2
LMArena Vision: humor11821227GPT-5.2
LMArena Vision: captioning11741267GPT-5.2
LMArena Vision: recognizing things11871232GPT-5.2
LMArena Vision: creative writing11821225GPT-5.2
LMArena DocumentNot measured1405Only GPT-5.2 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-4.1 Mini and GPT-5.2
BenchmarkGPT-4.1 MiniGPT-5.2Leader
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-5.2$0.0088Fits 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-5.2$0.130Fits in one request

GPT-4.1 Mini costs less

Agent loop

200K input + 10K output tokens

GPT-4.1 Mini$0.096Fits in one request
GPT-5.2$0.490Fits in one request

GPT-4.1 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-5.2
SpecificationOpenAI GPT-4.1 MiniOpenAI GPT-5.2
MakerOpenAIOpenAI
WeightsNo public weights listedNo public weights listed
ReleasedApril 14, 2025December 10, 2025
Context window1.05M400K
Input $/Mtok$0.40$1.75
Output $/Mtok$1.60$14.00
Coding index28.558.9
Independent measurements behind it22
Cost per solved task$1.818$1.91
SourceOpenRouter listingOpenRouter listing

Questions

Is GPT-4.1 Mini better than GPT-5.2 for coding?

Pick GPT-5.2 for coding: it scores 58.9 on the Vibe Coding Index against 28.5 for GPT-4.1 Mini. Pick GPT-4.1 Mini when output tokens cost 8.8x less, or when a solved task costs $1.818 against $1.91.

Which is cheaper, GPT-4.1 Mini or GPT-5.2?

GPT-4.1 Mini costs $0.40 per million input tokens and $1.60 per million output tokens; GPT-5.2 costs $1.75 and $14.00. Per solved SWE-bench Verified task, GPT-4.1 Mini costs $1.818 and GPT-5.2 $1.91.

Which has the bigger context window, GPT-4.1 Mini or GPT-5.2?

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

How many benchmarks is the GPT-4.1 Mini vs GPT-5.2 comparison based on?

79 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-5.2's on 2. 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-4-1-mini-vs-gpt-5-2" title="GPT-4.1 Mini vs GPT-5.2, 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-4-1-mini-vs-gpt-5-2">LLMBenchmark.ai, GPT-4.1 Mini vs GPT-5.2</a></p>