Enter opens the highlighted result. Esc closes.

GPT-5.4 Nano vs Mistral Medium 3.1

GPT-5.4 Nano leads Mistral Medium 3.1 on the Artificial Analysis Intelligence Index, 20.7 to 9.2, and GPT-5.4 Nano costs 1.6x less per output token ($1.25 vs $2.00 per million). Updated October 22, 2026; 58 benchmarks have a result for both.

Replace GPT-5.4 Nano Replace Mistral Medium 3.1
GPT-5.4 NanoOpenAI
Coding
44.8
Overall
45.7
Output $/M
$1.25
26
Mistral Medium 3.1Mistral AI
Coding
No data
Overall
No data
Output $/M
$2.00
32
vs boards won of 58 shared

GPT-5.4 Nano or Mistral Medium 3.1: which to pick

Only GPT-5.4 Nano has a coding score, 44.8 on the Vibe Coding Index; Mistral Medium 3.1 has none, so the two cannot be ranked on coding.

Pick Mistral Medium 3.1 for work measured by LMArena Text: coding or LMArena Text: software and IT, where it leads.

Model AGPT-5.4 NanoOpenAI44.8/1002 independent benchmarks$0.14 per solved taskModel BMistral Medium 3.1Mistral AINot benchmarkedNo coding benchmarkNo cost per solved task
Shared results
58
GPT-5.4 Nano only
27
Mistral Medium 3.1 only
16
Like-for-like categories
7 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-5.4 Nano 44.8 from 2 benchmarks, Mistral Medium 3.1 not benchmarked.
Widest category
Agentic work, 24.7 points apart on average over 2 shared benchmarks.
Widest single gap
AIME: GPT-5.4 Nano 88.8% against Mistral Medium 3.1 42.3%, 46.5 points apart on a 0 to 100 scale.
Output price
GPT-5.4 Nano $1.25 against Mistral Medium 3.1 $2.00 per million output tokens, 1.6x apart.
Context window
GPT-5.4 Nano takes 400K 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-5.4 NanoBarsMistral Medium 3.1Ties
Coding52
Intelligence10
Agentic work20
Reasoning53
Math12
Knowledge45
General820
All shared boards2632
CodingLike-for-likeSix of these boards feed the Vibe Coding Index52
Coding benchmarks for GPT-5.4 Nano and Mistral Medium 3.1
BenchmarkGPT-5.4 NanoMistral Medium 3.1Leader
AA Coding Index56.120.5GPT-5.4 Nano
LiveCodeBench (Vals AI)84.0%44.8%GPT-5.4 Nano
SWE-bench Verified (Vals AI)69.8%Not measuredOnly GPT-5.4 Nano measured
Vibe Code Bench (Vals AI)26.1%Not measuredOnly GPT-5.4 Nano measured
Code migration (Vals AI)14.5%Not measuredOnly GPT-5.4 Nano measured
Terminal-Bench 2.1 (Vals AI)41.6%Not measuredOnly GPT-5.4 Nano measured
LiveCodeBench (Artificial Analysis run)Not measured40.6%Only Mistral Medium 3.1 measured
SciCode47.2%32.4%GPT-5.4 Nano
Terminal-Bench Hard (Artificial Analysis run)42.4%10.6%GPT-5.4 Nano
WeirdML49.2%Not measuredOnly GPT-5.4 Nano measured
ALE-Bench1004.5210.2GPT-5.4 Nano
LMArena Text: coding14041433Mistral Medium 3.1
LMArena Text: software and IT14021436Mistral 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-5.4 Nano and Mistral Medium 3.1
BenchmarkGPT-5.4 NanoMistral Medium 3.1Leader
AA Intelligence Index20.79.2GPT-5.4 Nano
Epoch Capabilities Index146.0Not measuredOnly GPT-5.4 Nano measured
Agentic workLike-for-likePublic boards, shown as published, kept out of the index20
Agentic work benchmarks for GPT-5.4 Nano and Mistral Medium 3.1
BenchmarkGPT-5.4 NanoMistral Medium 3.1Leader
AA Agentic Index16.01.9GPT-5.4 Nano
Finance Agent (Vals AI)38.2%Not measuredOnly GPT-5.4 Nano measured
Tax Agent Bench (Vals AI)5.0%Not measuredOnly GPT-5.4 Nano measured
Legal Research Bench (Vals AI)6.3%Not measuredOnly GPT-5.4 Nano measured
Excel Modeling Benchmark (Vals AI)44.8%Not measuredOnly GPT-5.4 Nano measured
τ²-Bench Telecom76.0%40.6%GPT-5.4 Nano
Neither model has a result on the other 35 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index53
Reasoning benchmarks for GPT-5.4 Nano and Mistral Medium 3.1
BenchmarkGPT-5.4 NanoMistral Medium 3.1Leader
GPQA Diamond77.5%Not measuredOnly GPT-5.4 Nano measured
MMMU Pro (Vals AI)73.6%63.0%GPT-5.4 Nano
GPQA Diamond (Artificial Analysis run)81.7%58.8%GPT-5.4 Nano
Humanity's Last Exam (Artificial Analysis run)28.3%4.7%GPT-5.4 Nano
GPQA Diamond (Epoch AI run)78.5%Not measuredOnly GPT-5.4 Nano measured
ARC-AGI51.5%Not measuredOnly GPT-5.4 Nano measured
ARC-AGI-25.7%Not measuredOnly GPT-5.4 Nano measured
Chess puzzles45.0%Not measuredOnly GPT-5.4 Nano measured
Mystery game puzzles9.0%Not measuredOnly GPT-5.4 Nano measured
LMArena Text: hard prompts13811426Mistral Medium 3.1
LMArena Text: expert13961408Mistral Medium 3.1
LMArena Text: hard prompts in English13871435Mistral Medium 3.1
LMArena Vision: diagrams12101175GPT-5.4 Nano
LMArena Vision: homework12251165GPT-5.4 Nano
Kagi LLM Benchmark39.7%Not measuredOnly GPT-5.4 Nano measured
Neither model has a result on the other 7 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index12
Math benchmarks for GPT-5.4 Nano and Mistral Medium 3.1
BenchmarkGPT-5.4 NanoMistral Medium 3.1Leader
AIME88.8%42.3%GPT-5.4 Nano
MATH 500 (Vals AI)Not measured87.0%Only Mistral Medium 3.1 measured
MGSM (Vals AI)Not measured90.9%Only Mistral Medium 3.1 measured
AA Math IndexNot measured38.3Only Mistral Medium 3.1 measured
AIME 2025 (Artificial Analysis run)Not measured38.3%Only Mistral Medium 3.1 measured
OTIS Mock AIME87.8%Not measuredOnly GPT-5.4 Nano measured
FrontierMath, tiers 1 to 344.9%Not measuredOnly GPT-5.4 Nano measured
FrontierMath, tier 412.2%Not measuredOnly GPT-5.4 Nano measured
ProofBench5.0%Not measuredOnly GPT-5.4 Nano measured
LMArena Text: math14051408Mistral Medium 3.1
LMArena Text: mathematical work14091412Mistral Medium 3.1
Neither model has a result on the other 2 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index45
Knowledge benchmarks for GPT-5.4 Nano and Mistral Medium 3.1
BenchmarkGPT-5.4 NanoMistral Medium 3.1Leader
MMLU Pro77.2%75.3%GPT-5.4 Nano
LegalBench (Vals AI)77.9%62.0%GPT-5.4 Nano
CaseLaw (Vals AI)51.9%Not measuredOnly GPT-5.4 Nano measured
CorpFin (Vals AI)61.2%50.7%GPT-5.4 Nano
TaxEval (Vals AI)67.4%70.3%Mistral Medium 3.1
MortgageTax (Vals AI)59.1%36.5%GPT-5.4 Nano
MedQA (Vals AI)Not measured78.2%Only Mistral Medium 3.1 measured
MedCode (Vals AI)41.0%Not measuredOnly GPT-5.4 Nano measured
MMLU Pro (Artificial Analysis run)Not measured68.3%Only Mistral Medium 3.1 measured
SimpleQA Verified11.7%Not measuredOnly GPT-5.4 Nano measured
LMArena Text: science13741444Mistral Medium 3.1
LMArena Text: medicine and healthcare13691449Mistral Medium 3.1
LMArena Text: legal and government13681439Mistral Medium 3.1
LMArena Text: business and finance13661418Mistral Medium 3.1
Neither model has a result on the other 4 boards here
Web designDirectional onlyPublic boards, shown as published, kept out of the index8 boards, none shared
Web design benchmarks for GPT-5.4 Nano and Mistral Medium 3.1
BenchmarkGPT-5.4 NanoMistral Medium 3.1Leader
Design Arena: websitesNot measured1132Only Mistral Medium 3.1 measured
Design Arena: UI componentsNot measured1097Only Mistral Medium 3.1 measured
Design Arena: game devNot measured1073Only Mistral Medium 3.1 measured
Design Arena: data vizNot measured1144Only Mistral Medium 3.1 measured
Design Arena: 3DNot measured1081Only Mistral Medium 3.1 measured
Design Arena: all code categoriesNot measured1120Only Mistral Medium 3.1 measured
Design Arena: SVGNot measured992Only 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 index820
General benchmarks for GPT-5.4 Nano and Mistral Medium 3.1
BenchmarkGPT-5.4 NanoMistral Medium 3.1Leader
SAGE (Vals AI)38.1%Not measuredOnly GPT-5.4 Nano measured
MedScribe (Vals AI)77.1%Not measuredOnly GPT-5.4 Nano measured
Vals Multimodal Index47.6%Not measuredOnly GPT-5.4 Nano measured
IFBench75.9%39.8%GPT-5.4 Nano
Long context reasoning (AA-LCR)76.7%42.7%GPT-5.4 Nano
DTBench80.3%67.5%GPT-5.4 Nano
LMCA36.9%19.1%GPT-5.4 Nano
LMArena Text13721424Mistral Medium 3.1
LMArena Text: instruction following13621398Mistral Medium 3.1
LMArena Text: creative writing13151391Mistral Medium 3.1
LMArena Vision11961172GPT-5.4 Nano
LMArena Text: English13811438Mistral Medium 3.1
LMArena Text: non-English13591408Mistral Medium 3.1
LMArena Text: Chinese13911447Mistral Medium 3.1
LMArena Text: German13681432Mistral Medium 3.1
LMArena Text: Japanese13431379Mistral Medium 3.1
LMArena Text: Korean13211380Mistral Medium 3.1
LMArena Text: French13951460Mistral Medium 3.1
LMArena Text: Spanish13711433Mistral Medium 3.1
LMArena Text: Russian13631411Mistral Medium 3.1
LMArena Text: Polish13661430Mistral Medium 3.1
LMArena Text: multi-turn13821418Mistral Medium 3.1
LMArena Text: longer queries13651406Mistral Medium 3.1
LMArena Text: writing and language13381395Mistral Medium 3.1
LMArena Text: entertainment and media13251390Mistral Medium 3.1
LMArena Vision: English12021179GPT-5.4 Nano
LMArena Vision: Chinese12321190GPT-5.4 Nano
LMArena Vision: reading text12041175GPT-5.4 Nano
LMArena Vision: humor11611168Mistral Medium 3.1
LMArena Vision: captioningNot measured1145Only Mistral Medium 3.1 measured
LMArena Vision: recognizing things11411147Mistral Medium 3.1
LMArena Vision: creative writing11591200Mistral Medium 3.1
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-5.4 Nano and Mistral Medium 3.1
BenchmarkGPT-5.4 NanoMistral 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-5.4 Nano$0.0008Fits in one request
Mistral Medium 3.1$0.0014Fits in one request

GPT-5.4 Nano costs less

Repository review

50K input + 3K output tokens

GPT-5.4 Nano$0.014Fits in one request
Mistral Medium 3.1$0.026Fits in one request

GPT-5.4 Nano costs less

Agent loop

200K input + 10K output tokens

GPT-5.4 Nano$0.052Fits in one request
Mistral Medium 3.1$0.100Exceeds the context window

GPT-5.4 Nano 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-5.4 Nano and Mistral Medium 3.1
SpecificationOpenAI GPT-5.4 NanoMistral Medium 3.1
MakerOpenAIMistral AI
WeightsNo public weights listedNo public weights listed
ReleasedMarch 17, 2026August 13, 2025
Context window400K131K
Input $/Mtok$0.20$0.40
Output $/Mtok$1.25$2.00
Coding index44.8Not benchmarked
Independent measurements behind it20
Cost per solved task$0.14Not computable
SourceOpenRouter listingOpenRouter listing

Questions

Is GPT-5.4 Nano better than Mistral Medium 3.1 for coding?

Only GPT-5.4 Nano has a coding score, 44.8 on the Vibe Coding Index; Mistral Medium 3.1 has none, so the two cannot be ranked on coding. Pick Mistral Medium 3.1 for work measured by LMArena Text: coding or LMArena Text: software and IT, where it leads.

Which is cheaper, GPT-5.4 Nano or Mistral Medium 3.1?

GPT-5.4 Nano costs $0.20 per million input tokens and $1.25 per million output tokens; Mistral Medium 3.1 costs $0.40 and $2.00. Cost per solved task is known for GPT-5.4 Nano only.

Which has the bigger context window, GPT-5.4 Nano or Mistral Medium 3.1?

GPT-5.4 Nano, with 400K tokens against 131K.

How many benchmarks is the GPT-5.4 Nano vs Mistral Medium 3.1 comparison based on?

58 benchmarks have a result for both models as of October 22, 2026. GPT-5.4 Nano's coding index rests on 2 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