Enter opens the highlighted result. Esc closes.

GPT-4.1 vs Mistral Medium 3.1

GPT-4.1 leads Mistral Medium 3.1 on the Artificial Analysis Intelligence Index, 12.7 to 9.2, and Mistral Medium 3.1 costs 4.0x less per output token ($2.00 vs $8.00 per million). Updated October 21, 2026; 69 benchmarks have a result for both.

Replace GPT-4.1 Replace Mistral Medium 3.1
GPT-4.1OpenAI
Coding
No data
Overall
12.7
Output $/M
$8.00
31
Mistral Medium 3.1Mistral AI
Coding
No data
Overall
9.2
Output $/M
$2.00
38
vs boards won of 69 shared

GPT-4.1 or Mistral Medium 3.1: which to pick

Neither model has a coding score yet, so the two cannot be ranked on coding.

Pick GPT-4.1 for a larger context window (1.05M against 131K tokens) and work measured by LMArena Text: coding or LMArena Text: software and IT, where it leads.

Model AGPT-4.1OpenAINot benchmarkedNo coding benchmark$0.37 per solved taskModel BMistral Medium 3.1Mistral AINot benchmarkedNo coding benchmarkNo cost per solved task
Shared results
69
GPT-4.1 only
18
Mistral Medium 3.1 only
5
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, Mistral Medium 3.1 not benchmarked.
Widest category
Knowledge, 12.3 points apart on average over 11 shared benchmarks.
Widest single gap
MortgageTax (Vals AI): GPT-4.1 65.9% against Mistral Medium 3.1 36.5%, 29.5 points apart on a 0 to 100 scale.
Output price
GPT-4.1 $8.00 against Mistral Medium 3.1 $2.00 per million output tokens, 4.0x apart.
Context window
GPT-4.1 takes 1.05M tokens, Mistral Medium 3.1 131K.

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-4.1BarsMistral Medium 3.1Ties
Coding42
Intelligence10
Agentic work10
Reasoning44
Math16
Knowledge74
Web design15
General1217
All shared boards3138
CodingLike-for-likeSix of these boards feed the Vibe Coding Index42
Coding benchmarks for GPT-4.1 and Mistral Medium 3.1
BenchmarkGPT-4.1Mistral Medium 3.1Leader
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
AA Coding IndexNot measured20.5Only Mistral Medium 3.1 measured
LiveCodeBench (Vals AI)54.7%44.8%GPT-4.1
LiveCodeBench (Artificial Analysis run)45.7%40.6%GPT-4.1
SciCodeNot measured32.4%Only Mistral Medium 3.1 measured
Terminal-Bench Hard (Artificial Analysis run)13.6%10.6%GPT-4.1
WeirdML39.0%Not measuredOnly GPT-4.1 measured
ALE-Bench558.1210.2GPT-4.1
LMArena Text: coding13901433Mistral Medium 3.1
LMArena Text: software and IT13911436Mistral Medium 3.1
Neither model has a result on the other 26 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index10
Intelligence benchmarks for GPT-4.1 and Mistral Medium 3.1
BenchmarkGPT-4.1Mistral Medium 3.1Leader
AA Intelligence Index12.79.2GPT-4.1
Epoch Capabilities Index136.7Not measuredOnly GPT-4.1 measured
Agentic workLike-for-likePublic boards, shown as published, kept out of the index10
Agentic work benchmarks for GPT-4.1 and Mistral Medium 3.1
BenchmarkGPT-4.1Mistral Medium 3.1Leader
AA Agentic IndexNot measured1.9Only Mistral Medium 3.1 measured
τ²-Bench Telecom47.1%40.6%GPT-4.1
Neither model has a result on the other 37 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index44
Reasoning benchmarks for GPT-4.1 and Mistral Medium 3.1
BenchmarkGPT-4.1Mistral Medium 3.1Leader
GPQA Diamond65.4%Not measuredOnly GPT-4.1 measured
MMMU Pro (Vals AI)72.4%63.0%GPT-4.1
GPQA Diamond (Artificial Analysis run)66.6%58.8%GPT-4.1
Humanity's Last Exam (Artificial Analysis run)4.2%4.7%Mistral Medium 3.1
GPQA Diamond (Epoch AI run)66.9%Not measuredOnly GPT-4.1 measured
ARC-AGI5.5%Not measuredOnly GPT-4.1 measured
ARC-AGI-20.4%Not measuredOnly GPT-4.1 measured
SimpleBench27.0%Not measuredOnly GPT-4.1 measured
Chess puzzles3.0%Not measuredOnly GPT-4.1 measured
LMArena Text: hard prompts13841426Mistral Medium 3.1
LMArena Text: expert13641408Mistral Medium 3.1
LMArena Text: hard prompts in English13931435Mistral Medium 3.1
LMArena Vision: diagrams12151175GPT-4.1
LMArena Vision: homework12481165GPT-4.1
Neither model has a result on the other 7 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index16
Math benchmarks for GPT-4.1 and Mistral Medium 3.1
BenchmarkGPT-4.1Mistral Medium 3.1Leader
AIME39.6%42.3%Mistral Medium 3.1
MATH 500 (Vals AI)87.2%87.0%GPT-4.1
MGSM (Vals AI)87.7%90.9%Mistral Medium 3.1
AA Math Index34.738.3Mistral Medium 3.1
AIME 2025 (Artificial Analysis run)34.7%38.3%Mistral Medium 3.1
OTIS Mock AIME38.3%Not measuredOnly GPT-4.1 measured
FrontierMath, tiers 1 to 36.0%Not measuredOnly GPT-4.1 measured
MATH level 583.0%Not measuredOnly GPT-4.1 measured
LMArena Text: math13691408Mistral Medium 3.1
LMArena Text: mathematical work13601412Mistral Medium 3.1
Neither model has a result on the other 3 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index74
Knowledge benchmarks for GPT-4.1 and Mistral Medium 3.1
BenchmarkGPT-4.1Mistral Medium 3.1Leader
MMLU Pro80.5%75.3%GPT-4.1
LegalBench (Vals AI)83.1%62.0%GPT-4.1
CaseLaw (Vals AI)69.9%Not measuredOnly GPT-4.1 measured
CorpFin (Vals AI)63.0%50.7%GPT-4.1
TaxEval (Vals AI)75.1%70.3%GPT-4.1
MortgageTax (Vals AI)65.9%36.5%GPT-4.1
MedQA (Vals AI)91.2%78.2%GPT-4.1
MMLU Pro (Artificial Analysis run)80.6%68.3%GPT-4.1
SimpleQA Verified31.1%Not measuredOnly GPT-4.1 measured
GeoBench72.0%Not measuredOnly GPT-4.1 measured
LMArena Text: science13821444Mistral Medium 3.1
LMArena Text: medicine and healthcare13791449Mistral Medium 3.1
LMArena Text: legal and government13991439Mistral Medium 3.1
LMArena Text: business and finance13691418Mistral Medium 3.1
Neither model has a result on the other 3 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index15
Web design benchmarks for GPT-4.1 and Mistral Medium 3.1
BenchmarkGPT-4.1Mistral Medium 3.1Leader
Design Arena: websites10391133Mistral Medium 3.1
Design Arena: UI components10001100Mistral Medium 3.1
Design Arena: game dev10801074GPT-4.1
Design Arena: data viz11041144Mistral Medium 3.1
Design Arena: 3D8501081Mistral Medium 3.1
Design Arena: all code categories10261120Mistral Medium 3.1
Design Arena: SVGNot measured993Only Mistral Medium 3.1 measured
Design Arena: ASCII artNot measured997Only Mistral Medium 3.1 measured
Neither model has a result on the other 1 board here
GeneralLike-for-likePublic boards, shown as published, kept out of the index1217
General benchmarks for GPT-4.1 and Mistral Medium 3.1
BenchmarkGPT-4.1Mistral Medium 3.1Leader
IFBench43.0%39.8%GPT-4.1
Long context reasoning (AA-LCR)68.3%42.7%GPT-4.1
DTBench68.3%67.5%GPT-4.1
LMCA25.6%19.1%GPT-4.1
Fiction.LiveBench63.9%Not measuredOnly GPT-4.1 measured
LMArena Text13831424Mistral Medium 3.1
LMArena Text: instruction following13671398Mistral Medium 3.1
LMArena Text: creative writing13631391Mistral Medium 3.1
LMArena Vision12101172GPT-4.1
LMArena Text: English13921438Mistral Medium 3.1
LMArena Text: non-English13701408Mistral Medium 3.1
LMArena Text: Chinese13821447Mistral Medium 3.1
LMArena Text: German13811432Mistral Medium 3.1
LMArena Text: Japanese13191379Mistral Medium 3.1
LMArena Text: Korean13381380Mistral Medium 3.1
LMArena Text: French13821460Mistral Medium 3.1
LMArena Text: Spanish13761433Mistral Medium 3.1
LMArena Text: Russian13771411Mistral Medium 3.1
LMArena Text: Polish13891430Mistral Medium 3.1
LMArena Text: multi-turn13971418Mistral Medium 3.1
LMArena Text: longer queries13851406Mistral Medium 3.1
LMArena Text: writing and language13711395Mistral Medium 3.1
LMArena Text: entertainment and media13651390Mistral Medium 3.1
LMArena Vision: English12091179GPT-4.1
LMArena Vision: Chinese12261190GPT-4.1
LMArena Vision: reading text12181175GPT-4.1
LMArena Vision: humor11961168GPT-4.1
LMArena Vision: captioning12071145GPT-4.1
LMArena Vision: recognizing things12081147GPT-4.1
LMArena Vision: creative writing12101200GPT-4.1
Neither model has a result on the other 16 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 Mistral Medium 3.1
BenchmarkGPT-4.1Mistral Medium 3.1Leader
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
Mistral Medium 3.1$0.0014Fits in one request

Mistral Medium 3.1 costs less

Repository review

50K input + 3K output tokens

GPT-4.1$0.124Fits in one request
Mistral Medium 3.1$0.026Fits in one request

Mistral Medium 3.1 costs less

Agent loop

200K input + 10K output tokens

GPT-4.1$0.480Fits in one request
Mistral Medium 3.1$0.100Exceeds the context window

Mistral Medium 3.1 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 Mistral Medium 3.1
SpecificationOpenAI GPT-4.1Mistral Medium 3.1
MakerOpenAIMistral AI
WeightsNo public weights listedNo public weights listed
ReleasedApril 14, 2025August 13, 2025
Context window1.05M131K
Input $/Mtok$2.00$0.40
Output $/Mtok$8.00$2.00
Coding indexNot benchmarkedNot benchmarked
Independent measurements behind it00
Cost per solved task$0.37Not computable
SourceOpenRouter listingOpenRouter listing

Questions

Is GPT-4.1 better than Mistral Medium 3.1 for coding?

Neither model has a coding score yet, so the two cannot be ranked on coding. Pick GPT-4.1 for a larger context window (1.05M against 131K tokens) and work measured by LMArena Text: coding or LMArena Text: software and IT, where it leads.

Which is cheaper, GPT-4.1 or Mistral Medium 3.1?

GPT-4.1 costs $2.00 per million input tokens and $8.00 per million output tokens; Mistral Medium 3.1 costs $0.40 and $2.00. Cost per solved task is known for GPT-4.1 only.

Which has the bigger context window, GPT-4.1 or Mistral Medium 3.1?

GPT-4.1, with 1.05M tokens against 131K.

How many benchmarks is the GPT-4.1 vs Mistral Medium 3.1 comparison based on?

69 benchmarks have a result for both models as of October 21, 2026. GPT-4.1's coding index rests on 0 independent benchmarks and Mistral Medium 3.1's on 0. Where only one model has a result, the page says so instead of naming a winner.

Compare next