Enter opens the highlighted result. Esc closes.

GPT-5 vs Mistral Large 4

Mistral Large 4 leads GPT-5 on coding, 56.4 to 38.8 on the Vibe Coding Index, and Mistral Large 4 costs 2.4x less per output token ($4.18 vs $10.00 per million). Updated October 21, 2026; 57 benchmarks have a result for both.

Replace GPT-5 Replace Mistral Large 4
GPT-5OpenAI
Coding
38.8
Overall
51.5
Output $/M
$10.00
11
Mistral Large 4Mistral AI
Coding
56.4
Overall
54.6
Output $/M
$4.18
46
vs boards won of 57 shared

GPT-5 or Mistral Large 4: which to pick

Pick Mistral Large 4 for coding: it scores 56.4 on the Vibe Coding Index against 38.8 for GPT-5.

Pick GPT-5 for work measured by Chess puzzles or Mystery game puzzles, where it leads.

Model AGPT-5OpenAI38.8/1003 independent benchmarks$0.39 per solved taskModel BMistral Large 4Mistral AI56.4/1005 independent benchmarksNo cost per solved task
Shared results
57
GPT-5 only
56
Mistral Large 4 only
24
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 38.8 from 3 benchmarks, Mistral Large 4 56.4 from 5 benchmarks.
Widest category
Coding, 19.1 points apart on average over 6 shared benchmarks.
Widest single gap
Vibe Code Bench (Vals AI): GPT-5 20.1% against Mistral Large 4 78.4%, 58.3 points apart on a 0 to 100 scale.
Output price
GPT-5 $10.00 against Mistral Large 4 $4.18 per million output tokens, 2.4x apart.
Context window
GPT-5 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-5BarsMistral Large 4Ties
Coding06
Intelligence02
Reasoning26
Math15
Knowledge33
Web design08
General516
All shared boards1146
CodingLike-for-likeSix of these boards feed the Vibe Coding Index06
Coding benchmarks for GPT-5 and Mistral Large 4
BenchmarkGPT-5Mistral Large 4Leader
Aider polyglot88.0%Not measuredOnly GPT-5 measured
SWE-bench Verified74.4%Not measuredOnly GPT-5 measured
LiveBench codingNot measured60.0%Only Mistral Large 4 measured
LMArena WebDev14181543Mistral Large 4
AA Coding Index37.8Not measuredOnly GPT-5 measured
LiveCodeBench (Vals AI)85.9%Not measuredOnly GPT-5 measured
SWE-bench Verified (Vals AI)69.0%Not measuredOnly GPT-5 measured
Terminal-Bench 4 (Vals AI)Not measured27.8%Only Mistral Large 4 measured
Vibe Code Bench (Vals AI)20.1%78.4%Mistral Large 4
Code migration (Vals AI)Not measured30.6%Only Mistral Large 4 measured
IOI (Vals AI)Not measured45.3%Only Mistral Large 4 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
LiveCodeBench (Artificial Analysis run)84.6%Not measuredOnly GPT-5 measured
SciCodeNot measured54.2%Only Mistral Large 4 measured
Terminal-Bench Hard (Artificial Analysis run)37.9%Not measuredOnly GPT-5 measured
Terminal-Bench49.6%Not measuredOnly GPT-5 measured
FrontierCodeNot measured39.4%Only Mistral Large 4 measured
GSO-Bench6.9%Not measuredOnly GPT-5 measured
WeirdML60.7%Not measuredOnly GPT-5 measured
ALE-Bench807.61213.2Mistral Large 4
LMArena Text: coding14361478Mistral Large 4
LMArena Text: software and IT14201467Mistral Large 4
LMArena WebDev: ReactNot measured1559Only Mistral Large 4 measured
LMArena WebDev: HTML14271487Mistral Large 4
SciCode0.0%Not measuredOnly GPT-5 measured
Neither model has a result on the other 13 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
Intelligence benchmarks for GPT-5 and Mistral Large 4
BenchmarkGPT-5Mistral Large 4Leader
AA Intelligence Index23.038.4Mistral Large 4
Epoch Capabilities Index150.0150.0Mistral Large 4
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index16 boards, none shared
Agentic work benchmarks for GPT-5 and Mistral Large 4
BenchmarkGPT-5Mistral Large 4Leader
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)Not measured54.7%Only Mistral Large 4 measured
Tax Agent Bench (Vals AI)Not measured30.4%Only Mistral Large 4 measured
Legal Research Bench (Vals AI)Not measured31.7%Only Mistral Large 4 measured
Harvey's Legal Agent Benchmark (Vals AI)Not measured17.5%Only Mistral Large 4 measured
Excel Modeling Benchmark (Vals AI)Not measured56.2%Only Mistral Large 4 measured
BioMysteryBench (Vals AI)Not measured67.0%Only Mistral Large 4 measured
τ²-Bench Telecom86.5%Not measuredOnly GPT-5 measured
METR time horizons69.6%Not measuredOnly GPT-5 measured
Remote Labor Index1.7%Not measuredOnly GPT-5 measured
GDPval34.8%Not measuredOnly GPT-5 measured
BALROG32.8%Not measuredOnly GPT-5 measured
DeepResearch Bench49.6%Not measuredOnly GPT-5 measured
BrowseComp-Plus80.0%Not measuredOnly GPT-5 measured
Neither model has a result on the other 25 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index26
Reasoning benchmarks for GPT-5 and Mistral Large 4
BenchmarkGPT-5Mistral Large 4Leader
GPQA Diamond85.6%Not measuredOnly GPT-5 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)81.5%Not measuredOnly GPT-5 measured
GPQA Diamond (Artificial Analysis run)85.4%Not measuredOnly GPT-5 measured
Humanity's Last Exam (Artificial Analysis run)28.5%35.0%Mistral Large 4
GPQA Diamond (Epoch AI run)86.2%88.1%Mistral Large 4
ARC-AGI65.7%Not measuredOnly GPT-5 measured
ARC-AGI-29.9%Not measuredOnly GPT-5 measured
SimpleBench56.7%Not measuredOnly GPT-5 measured
Chess puzzles36.0%33.0%GPT-5
Mystery game puzzles23.0%17.0%GPT-5
EBR-bench12.7%Not measuredOnly GPT-5 measured
VPCT66.0%Not measuredOnly GPT-5 measured
LMArena Text: hard prompts14151444Mistral Large 4
LMArena Text: expert14191444Mistral Large 4
LMArena Text: hard prompts in English14191442Mistral Large 4
LMArena Vision: diagrams12521288Mistral Large 4
LMArena Vision: homework1278Not measuredOnly GPT-5 measured
Kagi LLM Benchmark72.7%Not measuredOnly GPT-5 measured
Neither model has a result on the other 2 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index15
Math benchmarks for GPT-5 and Mistral Large 4
BenchmarkGPT-5Mistral Large 4Leader
AIME93.4%Not measuredOnly GPT-5 measured
MATH 500 (Vals AI)96.0%Not measuredOnly GPT-5 measured
MGSM (Vals AI)92.8%Not measuredOnly GPT-5 measured
AA Math Index94.3Not measuredOnly GPT-5 measured
AIME 2025 (Artificial Analysis run)94.3%Not measuredOnly GPT-5 measured
OTIS Mock AIME91.4%98.3%Mistral Large 4
FrontierMath, tiers 1 to 355.4%58.6%Mistral Large 4
FrontierMath, tier 422.0%26.8%Mistral Large 4
ProofBench18.0%10.0%GPT-5
MATH level 598.1%Not measuredOnly GPT-5 measured
LMArena Text: math14071469Mistral Large 4
LMArena Text: mathematical work14051462Mistral Large 4
Neither model has a result on the other 1 board here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index33
Knowledge benchmarks for GPT-5 and Mistral Large 4
BenchmarkGPT-5Mistral Large 4Leader
MMLU Pro86.5%Not measuredOnly GPT-5 measured
LegalBench (Vals AI)86.0%Not measuredOnly GPT-5 measured
CaseLaw (Vals AI)66.5%Not measuredOnly GPT-5 measured
CorpFin (Vals AI)61.1%Not measuredOnly GPT-5 measured
TaxEval (Vals AI)73.4%Not measuredOnly GPT-5 measured
MortgageTax (Vals AI)65.5%Not measuredOnly GPT-5 measured
MedQA (Vals AI)96.3%Not measuredOnly GPT-5 measured
MedCode (Vals AI)49.6%40.7%GPT-5
MMLU Pro (Artificial Analysis run)87.1%Not measuredOnly GPT-5 measured
SimpleQA Verified50.1%20.0%GPT-5
GeoBench81.0%Not measuredOnly GPT-5 measured
LMArena Text: science14161448Mistral Large 4
LMArena Text: medicine and healthcare14131433Mistral Large 4
LMArena Text: legal and government14311425GPT-5
LMArena Text: business and finance14001439Mistral Large 4
FACTS Benchmark Suite56.5%Not measuredOnly GPT-5 measured
Neither model has a result on the other 2 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index08
Web design benchmarks for GPT-5 and Mistral Large 4
BenchmarkGPT-5Mistral Large 4Leader
Design Arena: websites11841258Mistral Large 4
Design Arena: UI components11801275Mistral Large 4
Design Arena: game dev11851226Mistral Large 4
Design Arena: data viz12211274Mistral Large 4
Design Arena: 3D10561253Mistral Large 4
Design Arena: all code categories11681259Mistral Large 4
Design Arena: SVG11891233Mistral Large 4
Design Arena: ASCII art11411202Mistral Large 4
LiveBench designNot measured65.6%Only Mistral Large 4 measured
GeneralLike-for-likePublic boards, shown as published, kept out of the index516
General benchmarks for GPT-5 and Mistral Large 4
BenchmarkGPT-5Mistral Large 4Leader
LiveBench data analysisNot measured76.5%Only Mistral Large 4 measured
SAGE (Vals AI)43.7%Not measuredOnly GPT-5 measured
MedScribe (Vals AI)83.7%80.4%GPT-5
IFBench73.1%Not measuredOnly GPT-5 measured
Long context reasoning (AA-LCR)78.2%81.3%Mistral Large 4
DTBench90.7%88.2%GPT-5
LMCA40.0%35.8%GPT-5
Fiction.LiveBench97.2%Not measuredOnly GPT-5 measured
Creative writing (Lech Mazur)86.0%Not measuredOnly GPT-5 measured
Surface Evolver BenchNot measured28.1%Only Mistral Large 4 measured
Furniture assemblyNot measured20.8%Only Mistral Large 4 measured
LMArena Text14061431Mistral Large 4
LMArena Text: instruction following13881422Mistral Large 4
LMArena Text: creative writing13651363GPT-5
LMArena Vision12321272Mistral Large 4
LMArena Text: English14091433Mistral Large 4
LMArena Text: non-English13971422Mistral Large 4
LMArena Text: Chinese14221492Mistral Large 4
LMArena Text: German1416Not measuredOnly GPT-5 measured
LMArena Text: Japanese14091415Mistral Large 4
LMArena Text: Korean1360Not measuredOnly GPT-5 measured
LMArena Text: French14091492Mistral Large 4
LMArena Text: Spanish13991455Mistral Large 4
LMArena Text: Russian14071417Mistral Large 4
LMArena Text: Polish1431Not measuredOnly GPT-5 measured
LMArena Text: multi-turn14261435Mistral Large 4
LMArena Text: longer queries13991428Mistral Large 4
LMArena Text: writing and language13841386Mistral Large 4
LMArena Text: entertainment and media13791378GPT-5
LMArena Vision: English12311283Mistral Large 4
LMArena Vision: Chinese1267Not measuredOnly GPT-5 measured
LMArena Vision: reading text12461284Mistral Large 4
LMArena Vision: humor1219Not measuredOnly GPT-5 measured
LMArena Vision: captioning1212Not measuredOnly GPT-5 measured
LMArena Vision: recognizing things1263Not measuredOnly GPT-5 measured
LMArena Vision: creative writing1210Not measuredOnly GPT-5 measured
Neither model has a result on the other 10 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for GPT-5 and Mistral Large 4
BenchmarkGPT-5Mistral 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$0.0063Fits in one request
Mistral Large 4$0.0034Fits in one request

Mistral Large 4 costs less

Repository review

50K input + 3K output tokens

GPT-5$0.092Fits in one request
Mistral Large 4$0.081Fits in one request

Mistral Large 4 costs less

Agent loop

200K input + 10K output tokens

GPT-5$0.350Fits in one request
Mistral Large 4$0.314Fits in one request

Mistral Large 4 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 and Mistral Large 4
SpecificationOpenAI GPT-5Mistral Large 4
MakerOpenAIMistral AI
WeightsNo public weights listedNo public weights listed
ReleasedAugust 7, 2025October 6, 2026
Context window400K1.05M
Input $/Mtok$1.25$1.36
Output $/Mtok$10.00$4.18
Coding index38.856.4
Independent measurements behind it35
Cost per solved task$0.39Not computable
SourceOpenRouter listingOpenRouter listing

Questions

Is GPT-5 better than Mistral Large 4 for coding?

Pick Mistral Large 4 for coding: it scores 56.4 on the Vibe Coding Index against 38.8 for GPT-5. Pick GPT-5 for work measured by Chess puzzles or Mystery game puzzles, where it leads.

Which is cheaper, GPT-5 or Mistral Large 4?

GPT-5 costs $1.25 per million input tokens and $10.00 per million output tokens; Mistral Large 4 costs $1.36 and $4.18. Cost per solved task is known for GPT-5 only.

Which has the bigger context window, GPT-5 or Mistral Large 4?

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

How many benchmarks is the GPT-5 vs Mistral Large 4 comparison based on?

57 benchmarks have a result for both models as of October 21, 2026. GPT-5's coding index rests on 3 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-vs-mistral-large-4-0" title="GPT-5 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-vs-mistral-large-4-0">LLMBenchmark.ai, GPT-5 vs Mistral Large 4</a></p>