Enter opens the highlighted result. Esc closes.

GPT-5.4 Nano vs Mistral Large 4

Mistral Large 4 leads GPT-5.4 Nano on coding, 56.4 to 44.8 on the Vibe Coding Index, and GPT-5.4 Nano costs 3.3x less per output token ($1.25 vs $4.18 per million). Updated October 22, 2026; 53 benchmarks have a result for both.

Replace GPT-5.4 Nano Replace Mistral Large 4
GPT-5.4 NanoOpenAI
Coding
44.8
Overall
45.7
Output $/M
$1.25
3
Mistral Large 4Mistral AI
Coding
56.4
Overall
54.6
Output $/M
$4.18
50
vs boards won of 53 shared

GPT-5.4 Nano or Mistral Large 4: which to pick

Pick Mistral Large 4 for coding: it scores 56.4 on the Vibe Coding Index against 44.8 for GPT-5.4 Nano.

Pick GPT-5.4 Nano for output tokens 3.3x cheaper ($1.25 vs $4.18 per million) and work measured by Chess puzzles or MedCode (Vals AI), where it leads.

Model AGPT-5.4 NanoOpenAI44.8/1002 independent benchmarks$0.14 per solved taskModel BMistral Large 4Mistral AI56.4/1005 independent benchmarksNo cost per solved task
Shared results
53
GPT-5.4 Nano only
32
Mistral Large 4 only
28
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 Large 4 56.4 from 5 benchmarks.
Widest category
Agentic work, 19.7 points apart on average over 4 shared benchmarks.
Widest single gap
Vibe Code Bench (Vals AI): GPT-5.4 Nano 26.1% against Mistral Large 4 78.4%, 52.3 points apart on a 0 to 100 scale.
Output price
GPT-5.4 Nano $1.25 against Mistral Large 4 $4.18 per million output tokens, 3.3x apart.
Context window
GPT-5.4 Nano takes 400K tokens, Mistral Large 4 1.05M.

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 Large 4Ties
Coding06
Intelligence02
Agentic work04
Reasoning17
Math06
Knowledge15
General120
All shared boards350
CodingLike-for-likeSix of these boards feed the Vibe Coding Index06
Coding benchmarks for GPT-5.4 Nano and Mistral Large 4
BenchmarkGPT-5.4 NanoMistral Large 4Leader
LiveBench codingNot measured60.0%Only Mistral Large 4 measured
LMArena WebDevNot measured1543Only Mistral Large 4 measured
AA Coding Index56.1Not measuredOnly GPT-5.4 Nano measured
LiveCodeBench (Vals AI)84.0%Not measuredOnly GPT-5.4 Nano measured
SWE-bench Verified (Vals AI)69.8%Not measuredOnly GPT-5.4 Nano measured
Terminal-Bench 4 (Vals AI)Not measured27.8%Only Mistral Large 4 measured
Vibe Code Bench (Vals AI)26.1%78.4%Mistral Large 4
Code migration (Vals AI)14.5%30.6%Mistral Large 4
IOI (Vals AI)Not measured45.3%Only Mistral Large 4 measured
Terminal-Bench 2.1 (Vals AI)41.6%Not measuredOnly GPT-5.4 Nano measured
SWE-bench Multimodal (Vals AI)Not measured33.1%Only Mistral Large 4 measured
Vibe Code Bench 1-100 (Vals AI)Not measured14.3%Only Mistral Large 4 measured
SciCode47.2%54.2%Mistral Large 4
Terminal-Bench Hard (Artificial Analysis run)42.4%Not measuredOnly GPT-5.4 Nano measured
FrontierCodeNot measured39.4%Only Mistral Large 4 measured
WeirdML49.2%Not measuredOnly GPT-5.4 Nano measured
ALE-Bench1004.51213.2Mistral Large 4
LMArena Text: coding14041478Mistral Large 4
LMArena Text: software and IT14021467Mistral Large 4
LMArena WebDev: ReactNot measured1559Only Mistral Large 4 measured
LMArena WebDev: HTMLNot measured1487Only Mistral Large 4 measured
Neither model has a result on the other 18 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
Intelligence benchmarks for GPT-5.4 Nano and Mistral Large 4
BenchmarkGPT-5.4 NanoMistral Large 4Leader
AA Intelligence Index20.738.4Mistral Large 4
Epoch Capabilities Index146.0150.0Mistral Large 4
Agentic workLike-for-likePublic boards, shown as published, kept out of the index04
Agentic work benchmarks for GPT-5.4 Nano and Mistral Large 4
BenchmarkGPT-5.4 NanoMistral Large 4Leader
AA Agentic Index16.0Not measuredOnly GPT-5.4 Nano measured
LiveBench researchNot measured28.1%Only Mistral Large 4 measured
LiveBench browserNot measured8.0%Only Mistral Large 4 measured
LiveBench long agenticNot measured11.8%Only Mistral Large 4 measured
Finance Agent (Vals AI)38.2%54.7%Mistral Large 4
Tax Agent Bench (Vals AI)5.0%30.4%Mistral Large 4
Legal Research Bench (Vals AI)6.3%31.7%Mistral Large 4
Harvey's Legal Agent Benchmark (Vals AI)Not measured17.5%Only Mistral Large 4 measured
Excel Modeling Benchmark (Vals AI)44.8%56.2%Mistral Large 4
BioMysteryBench (Vals AI)Not measured67.0%Only Mistral Large 4 measured
τ²-Bench Telecom76.0%Not measuredOnly GPT-5.4 Nano measured
Neither model has a result on the other 30 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index17
Reasoning benchmarks for GPT-5.4 Nano and Mistral Large 4
BenchmarkGPT-5.4 NanoMistral Large 4Leader
GPQA Diamond77.5%Not measuredOnly GPT-5.4 Nano measured
LiveBench reasoningNot measured83.9%Only Mistral Large 4 measured
MysteryMechanism (Vals AI)Not measured12.2%Only Mistral Large 4 measured
MMMU Pro (Vals AI)73.6%Not measuredOnly GPT-5.4 Nano measured
GPQA Diamond (Artificial Analysis run)81.7%Not measuredOnly GPT-5.4 Nano measured
Humanity's Last Exam (Artificial Analysis run)28.3%35.0%Mistral Large 4
GPQA Diamond (Epoch AI run)78.5%88.1%Mistral Large 4
ARC-AGI51.5%Not measuredOnly GPT-5.4 Nano measured
ARC-AGI-25.7%Not measuredOnly GPT-5.4 Nano measured
Chess puzzles45.0%33.0%GPT-5.4 Nano
Mystery game puzzles9.0%17.0%Mistral Large 4
LMArena Text: hard prompts13811444Mistral Large 4
LMArena Text: expert13961444Mistral Large 4
LMArena Text: hard prompts in English13871442Mistral Large 4
LMArena Vision: diagrams12101288Mistral Large 4
LMArena Vision: homework1225Not measuredOnly GPT-5.4 Nano measured
Kagi LLM Benchmark39.7%Not measuredOnly GPT-5.4 Nano measured
Neither model has a result on the other 5 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index06
Math benchmarks for GPT-5.4 Nano and Mistral Large 4
BenchmarkGPT-5.4 NanoMistral Large 4Leader
AIME88.8%Not measuredOnly GPT-5.4 Nano measured
OTIS Mock AIME87.8%98.3%Mistral Large 4
FrontierMath, tiers 1 to 344.9%58.6%Mistral Large 4
FrontierMath, tier 412.2%26.8%Mistral Large 4
ProofBench5.0%10.0%Mistral Large 4
LMArena Text: math14051469Mistral Large 4
LMArena Text: mathematical work14091462Mistral Large 4
Neither model has a result on the other 6 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index15
Knowledge benchmarks for GPT-5.4 Nano and Mistral Large 4
BenchmarkGPT-5.4 NanoMistral Large 4Leader
MMLU Pro77.2%Not measuredOnly GPT-5.4 Nano measured
LegalBench (Vals AI)77.9%Not measuredOnly GPT-5.4 Nano measured
CaseLaw (Vals AI)51.9%Not measuredOnly GPT-5.4 Nano measured
CorpFin (Vals AI)61.2%Not measuredOnly GPT-5.4 Nano measured
TaxEval (Vals AI)67.4%Not measuredOnly GPT-5.4 Nano measured
MortgageTax (Vals AI)59.1%Not measuredOnly GPT-5.4 Nano measured
MedCode (Vals AI)41.0%40.7%GPT-5.4 Nano
SimpleQA Verified11.7%20.0%Mistral Large 4
LMArena Text: science13741448Mistral Large 4
LMArena Text: medicine and healthcare13691433Mistral Large 4
LMArena Text: legal and government13681425Mistral Large 4
LMArena Text: business and finance13661439Mistral Large 4
Neither model has a result on the other 6 boards here
Web designDirectional onlyPublic boards, shown as published, kept out of the index9 boards, none shared
Web design benchmarks for GPT-5.4 Nano and Mistral Large 4
BenchmarkGPT-5.4 NanoMistral Large 4Leader
Design Arena: websitesNot measured1257Only Mistral Large 4 measured
Design Arena: UI componentsNot measured1272Only Mistral Large 4 measured
Design Arena: game devNot measured1225Only Mistral Large 4 measured
Design Arena: data vizNot measured1275Only Mistral Large 4 measured
Design Arena: 3DNot measured1252Only Mistral Large 4 measured
Design Arena: all code categoriesNot measured1259Only Mistral Large 4 measured
Design Arena: SVGNot measured1232Only Mistral Large 4 measured
Design Arena: ASCII artNot measured1202Only Mistral Large 4 measured
LiveBench designNot measured65.6%Only Mistral Large 4 measured
GeneralLike-for-likePublic boards, shown as published, kept out of the index120
General benchmarks for GPT-5.4 Nano and Mistral Large 4
BenchmarkGPT-5.4 NanoMistral Large 4Leader
LiveBench data analysisNot measured76.5%Only Mistral Large 4 measured
SAGE (Vals AI)38.1%Not measuredOnly GPT-5.4 Nano measured
MedScribe (Vals AI)77.1%80.4%Mistral Large 4
Vals Multimodal Index47.6%Not measuredOnly GPT-5.4 Nano measured
IFBench75.9%Not measuredOnly GPT-5.4 Nano measured
Long context reasoning (AA-LCR)76.7%81.3%Mistral Large 4
DTBench80.3%88.2%Mistral Large 4
LMCA36.9%35.8%GPT-5.4 Nano
Surface Evolver BenchNot measured28.1%Only Mistral Large 4 measured
Furniture assemblyNot measured20.8%Only Mistral Large 4 measured
LMArena Text13721431Mistral Large 4
LMArena Text: instruction following13621422Mistral Large 4
LMArena Text: creative writing13151363Mistral Large 4
LMArena Vision11961272Mistral Large 4
LMArena Text: English13811433Mistral Large 4
LMArena Text: non-English13591422Mistral Large 4
LMArena Text: Chinese13911492Mistral Large 4
LMArena Text: German1368Not measuredOnly GPT-5.4 Nano measured
LMArena Text: Japanese13431415Mistral Large 4
LMArena Text: Korean1321Not measuredOnly GPT-5.4 Nano measured
LMArena Text: French13951492Mistral Large 4
LMArena Text: Spanish13711455Mistral Large 4
LMArena Text: Russian13631417Mistral Large 4
LMArena Text: Polish1366Not measuredOnly GPT-5.4 Nano measured
LMArena Text: multi-turn13821435Mistral Large 4
LMArena Text: longer queries13651428Mistral Large 4
LMArena Text: writing and language13381386Mistral Large 4
LMArena Text: entertainment and media13251378Mistral Large 4
LMArena Vision: English12021283Mistral Large 4
LMArena Vision: Chinese1232Not measuredOnly GPT-5.4 Nano measured
LMArena Vision: reading text12041284Mistral Large 4
LMArena Vision: humor1161Not measuredOnly GPT-5.4 Nano measured
LMArena Vision: recognizing things1141Not measuredOnly GPT-5.4 Nano measured
LMArena Vision: creative writing1159Not measuredOnly GPT-5.4 Nano measured
Neither model has a result on the other 12 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 Large 4
BenchmarkGPT-5.4 NanoMistral Large 4Leader
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 Large 4$0.0034Fits 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 Large 4$0.081Fits 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 Large 4$0.314Fits in one request

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 Large 4
SpecificationOpenAI GPT-5.4 NanoMistral Large 4
MakerOpenAIMistral AI
WeightsNo public weights listedNo public weights listed
ReleasedMarch 17, 2026October 6, 2026
Context window400K1.05M
Input $/Mtok$0.20$1.36
Output $/Mtok$1.25$4.18
Coding index44.856.4
Independent measurements behind it25
Cost per solved task$0.14Not computable
SourceOpenRouter listingOpenRouter listing

Questions

Is GPT-5.4 Nano better than Mistral Large 4 for coding?

Pick Mistral Large 4 for coding: it scores 56.4 on the Vibe Coding Index against 44.8 for GPT-5.4 Nano. Pick GPT-5.4 Nano for output tokens 3.3x cheaper ($1.25 vs $4.18 per million) and work measured by Chess puzzles or MedCode (Vals AI), where it leads.

Which is cheaper, GPT-5.4 Nano or Mistral Large 4?

GPT-5.4 Nano costs $0.20 per million input tokens and $1.25 per million output tokens; Mistral Large 4 costs $1.36 and $4.18. Cost per solved task is known for GPT-5.4 Nano only.

Which has the bigger context window, GPT-5.4 Nano or Mistral Large 4?

Mistral Large 4, with 1.05M tokens against 400K.

How many benchmarks is the GPT-5.4 Nano vs Mistral Large 4 comparison based on?

53 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 Large 4's on 5. 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-5-4-nano-vs-mistral-large-4-0" title="GPT-5.4 Nano vs Mistral Large 4, 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-5-4-nano-vs-mistral-large-4-0">LLMBenchmark.ai, GPT-5.4 Nano vs Mistral Large 4</a></p>