Enter opens the highlighted result. Esc closes.

GPT-4.1 vs GPT-5.1

GPT-5.1 leads GPT-4.1 on the Artificial Analysis Intelligence Index, 24.7 to 12.7, and GPT-4.1 costs 1.3x less per output token ($8.00 vs $10.00 per million). Updated October 22, 2026; 80 benchmarks have a result for both.

Replace GPT-4.1 Replace GPT-5.1
GPT-4.1OpenAI
Coding
No data
Overall
36.5
Output $/M
$8.00
3
GPT-5.1OpenAI
Coding
40.4
Overall
55.0
Output $/M
$10.00
77
vs boards won of 80 shared

GPT-4.1 or GPT-5.1: which to pick

Only GPT-5.1 has a coding score, 40.4 on the Vibe Coding Index; GPT-4.1 has none, so the two cannot be ranked on coding.

Pick GPT-4.1 for output tokens 1.3x cheaper ($8.00 vs $10.00 per million) and a lower cost per solved task ($0.37 against $1.02).

Model AGPT-4.1OpenAINot benchmarkedNo coding benchmark$0.37 per solved taskModel BGPT-5.1OpenAI40.4/1003 independent benchmarks$1.02 per solved task
Shared results
80
GPT-4.1 only
12
GPT-5.1 only
21
Like-for-like categories
8 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-4.1 not benchmarked, GPT-5.1 40.4 from 3 benchmarks.
Widest category
Math, 36.5 points apart on average over 7 shared benchmarks.
Widest single gap
ARC-AGI: GPT-4.1 5.5% against GPT-5.1 72.8%, 67.3 points apart on a 0 to 100 scale.
Output price
GPT-4.1 $8.00 against GPT-5.1 $10.00 per million output tokens, 1.3x apart.
Context window
GPT-4.1 takes 1.05M tokens, GPT-5.1 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-5.1Ties
Coding07
Intelligence02
Agentic work01
Reasoning014
Math07
Knowledge311
Web design06
General029
All shared boards377
CodingLike-for-likeSix of these boards feed the Vibe Coding Index07
Coding benchmarks for GPT-4.1 and GPT-5.1
BenchmarkGPT-4.1GPT-5.1Leader
Aider polyglot52.4%Not measuredOnly GPT-4.1 measured
SWE-bench Verified39.6%66.0%GPT-5.1
SWE-bench Multimodal31.1%Not measuredOnly GPT-4.1 measured
LMArena WebDevNot measured1396Only GPT-5.1 measured
AA Coding IndexNot measured49.4Only GPT-5.1 measured
LiveCodeBench (Vals AI)54.7%86.5%GPT-5.1
SWE-bench Verified (Vals AI)Not measured69.8%Only GPT-5.1 measured
Vibe Code Bench (Vals AI)Not measured24.6%Only GPT-5.1 measured
LiveCodeBench (Artificial Analysis run)45.7%86.8%GPT-5.1
Terminal-Bench Hard (Artificial Analysis run)13.6%45.5%GPT-5.1
Terminal-BenchNot measured47.6%Only GPT-5.1 measured
GSO-BenchNot measured13.7%Only GPT-5.1 measured
WeirdML39.0%60.8%GPT-5.1
ALE-Bench558.1Not measuredOnly GPT-4.1 measured
LMArena Text: coding13901453GPT-5.1
LMArena Text: software and IT13911454GPT-5.1
LMArena WebDev: ReactNot measured1307Only GPT-5.1 measured
LMArena WebDev: HTMLNot measured1405Only GPT-5.1 measured
LMArena WebDev: from an imageNot measured1421Only GPT-5.1 measured
SciCode4.6%Not measuredOnly GPT-4.1 measured
Neither model has a result on the other 19 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
Intelligence benchmarks for GPT-4.1 and GPT-5.1
BenchmarkGPT-4.1GPT-5.1Leader
AA Intelligence Index12.724.7GPT-5.1
Epoch Capabilities Index136.7149.8GPT-5.1
Agentic workLike-for-likePublic boards, shown as published, kept out of the index01
Agentic work benchmarks for GPT-4.1 and GPT-5.1
BenchmarkGPT-4.1GPT-5.1Leader
τ²-Bench Telecom47.1%81.9%GPT-5.1
DeepResearch BenchNot measured42.8%Only GPT-5.1 measured
Vending-Bench 2Not measured$1,473Only GPT-5.1 measured
Berkeley Function Calling Leaderboard (BFCL)54.0%Not measuredOnly GPT-4.1 measured
BrowseComp-Plus36.4%Not measuredOnly GPT-4.1 measured
Neither model has a result on the other 36 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index014
Reasoning benchmarks for GPT-4.1 and GPT-5.1
BenchmarkGPT-4.1GPT-5.1Leader
GPQA Diamond65.4%86.6%GPT-5.1
MMMU Pro (Vals AI)72.4%83.2%GPT-5.1
GPQA Diamond (Artificial Analysis run)66.6%87.3%GPT-5.1
Humanity's Last Exam (Artificial Analysis run)4.2%28.5%GPT-5.1
GPQA Diamond (Epoch AI run)66.9%87.6%GPT-5.1
ARC-AGI5.5%72.8%GPT-5.1
ARC-AGI-20.4%17.6%GPT-5.1
SimpleBench27.0%53.2%GPT-5.1
Chess puzzles3.0%42.0%GPT-5.1
Mystery game puzzlesNot measured19.0%Only GPT-5.1 measured
VPCTNot measured58.7%Only GPT-5.1 measured
LMArena Text: hard prompts13841457GPT-5.1
LMArena Text: expert13641470GPT-5.1
LMArena Text: hard prompts in English13931462GPT-5.1
LMArena Vision: diagrams12151264GPT-5.1
LMArena Vision: homework12481272GPT-5.1
Kagi LLM Benchmark52.3%Not measuredOnly GPT-4.1 measured
Neither model has a result on the other 5 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index07
Math benchmarks for GPT-4.1 and GPT-5.1
BenchmarkGPT-4.1GPT-5.1Leader
AIME39.6%93.3%GPT-5.1
MATH 500 (Vals AI)87.2%Not measuredOnly GPT-4.1 measured
MGSM (Vals AI)87.7%93.0%GPT-5.1
AA Math Index34.794.0GPT-5.1
AIME 2025 (Artificial Analysis run)34.7%94.0%GPT-5.1
OTIS Mock AIME38.3%88.6%GPT-5.1
FrontierMath, tiers 1 to 36.0%Not measuredOnly GPT-4.1 measured
MATH level 583.0%Not measuredOnly GPT-4.1 measured
LMArena Text: math13691446GPT-5.1
LMArena Text: mathematical work13601449GPT-5.1
Neither model has a result on the other 3 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index311
Knowledge benchmarks for GPT-4.1 and GPT-5.1
BenchmarkGPT-4.1GPT-5.1Leader
MMLU Pro80.5%86.4%GPT-5.1
LegalBench (Vals AI)83.1%85.7%GPT-5.1
CaseLaw (Vals AI)69.9%73.4%GPT-5.1
CorpFin (Vals AI)63.0%63.8%GPT-5.1
TaxEval (Vals AI)75.1%74.9%GPT-4.1
MortgageTax (Vals AI)65.9%61.4%GPT-4.1
MedQA (Vals AI)91.2%96.4%GPT-5.1
MedCode (Vals AI)Not measured52.7%Only GPT-5.1 measured
MMLU Pro (Artificial Analysis run)80.6%87.0%GPT-5.1
SimpleQA Verified31.1%48.0%GPT-5.1
GeoBench72.0%Not measuredOnly GPT-4.1 measured
LMArena Text: science13821459GPT-5.1
LMArena Text: medicine and healthcare13791456GPT-5.1
LMArena Text: legal and government13991459GPT-5.1
LMArena Text: business and finance13691431GPT-5.1
FACTS Benchmark Suite45.8%45.0%GPT-4.1
Neither model has a result on the other 2 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index06
Web design benchmarks for GPT-4.1 and GPT-5.1
BenchmarkGPT-4.1GPT-5.1Leader
Design Arena: websites10381187GPT-5.1
Design Arena: UI components9971163GPT-5.1
Design Arena: game dev10791178GPT-5.1
Design Arena: data viz11041204GPT-5.1
Design Arena: 3D8491060GPT-5.1
Design Arena: all code categories10251170GPT-5.1
Design Arena: SVGNot measured1149Only GPT-5.1 measured
Design Arena: ASCII artNot measured1119Only GPT-5.1 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 and GPT-5.1
BenchmarkGPT-4.1GPT-5.1Leader
SAGE (Vals AI)Not measured43.2%Only GPT-5.1 measured
MedScribe (Vals AI)Not measured88.1%Only GPT-5.1 measured
IFBench43.0%72.9%GPT-5.1
Long context reasoning (AA-LCR)68.3%80.0%GPT-5.1
DTBench68.3%90.1%GPT-5.1
LMCA25.6%43.9%GPT-5.1
Fiction.LiveBench63.9%Not measuredOnly GPT-4.1 measured
CL-benchNot measured23.7%Only GPT-5.1 measured
CL-bench LifeNot measured17.3%Only GPT-5.1 measured
LMArena Text13831443GPT-5.1
LMArena Text: instruction following13671443GPT-5.1
LMArena Text: creative writing13631427GPT-5.1
LMArena Vision12101250GPT-5.1
LMArena Text: English13921451GPT-5.1
LMArena Text: non-English13701431GPT-5.1
LMArena Text: Chinese13821495GPT-5.1
LMArena Text: German13811438GPT-5.1
LMArena Text: Japanese13191453GPT-5.1
LMArena Text: Korean13381401GPT-5.1
LMArena Text: French13821450GPT-5.1
LMArena Text: Spanish13761433GPT-5.1
LMArena Text: Russian13771435GPT-5.1
LMArena Text: Polish13891440GPT-5.1
LMArena Text: multi-turn13971450GPT-5.1
LMArena Text: longer queries13851448GPT-5.1
LMArena Text: writing and language13711428GPT-5.1
LMArena Text: entertainment and media13651415GPT-5.1
LMArena Vision: English12091252GPT-5.1
LMArena Vision: Chinese12261270GPT-5.1
LMArena Vision: reading text12181255GPT-5.1
LMArena Vision: humor11961263GPT-5.1
LMArena Vision: captioning12071252GPT-5.1
LMArena Vision: recognizing things12081232GPT-5.1
LMArena Vision: creative writing12101266GPT-5.1
LMArena DocumentNot measured1403Only GPT-5.1 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 and GPT-5.1
BenchmarkGPT-4.1GPT-5.1Leader
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-5.1$0.0063Fits in one request

GPT-4.1 costs less

Repository review

50K input + 3K output tokens

GPT-4.1$0.124Fits in one request
GPT-5.1$0.092Fits in one request

GPT-5.1 costs less

Agent loop

200K input + 10K output tokens

GPT-4.1$0.480Fits in one request
GPT-5.1$0.350Fits in one request

GPT-5.1 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-5.1
SpecificationOpenAI GPT-4.1OpenAI GPT-5.1
MakerOpenAIOpenAI
WeightsNo public weights listedNo public weights listed
ReleasedApril 14, 2025November 13, 2025
Context window1.05M400K
Input $/Mtok$2.00$1.25
Output $/Mtok$8.00$10.00
Coding indexNot benchmarked40.4
Independent measurements behind it03
Cost per solved task$0.37$1.02
SourceOpenRouter listingOpenRouter listing

Questions

Is GPT-4.1 better than GPT-5.1 for coding?

Only GPT-5.1 has a coding score, 40.4 on the Vibe Coding Index; GPT-4.1 has none, so the two cannot be ranked on coding. Pick GPT-4.1 for output tokens 1.3x cheaper ($8.00 vs $10.00 per million) and a lower cost per solved task ($0.37 against $1.02).

Which is cheaper, GPT-4.1 or GPT-5.1?

GPT-4.1 costs $2.00 per million input tokens and $8.00 per million output tokens; GPT-5.1 costs $1.25 and $10.00. Per solved SWE-bench Verified task, GPT-4.1 costs $0.37 and GPT-5.1 $1.02.

Which has the bigger context window, GPT-4.1 or GPT-5.1?

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

How many benchmarks is the GPT-4.1 vs GPT-5.1 comparison based on?

80 benchmarks have a result for both models as of October 22, 2026. GPT-4.1's coding index rests on 0 independent benchmarks and GPT-5.1's on 3. Where only one model has a result, the page says so instead of naming a winner.

Compare next