Enter opens the highlighted result. Esc closes.

GPT-5 vs Mistral Medium 3.1

Updated October 21, 2026. 72 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.

Replace GPT-5 Replace Mistral Medium 3.1
GPT-5OpenAI
Coding
38.8
Overall
23.0
Output $/M
$10.00
48
Mistral Medium 3.1Mistral AI
Coding
No data
Overall
9.2
Output $/M
$2.00
24
vs boards won of 72 shared

Decision reading

Only GPT-5 has a coding score, 38.8 on the Vibe Coding Index; Mistral Medium 3.1 has none, so the two cannot be ranked on coding.

Mistral Medium 3.1 has the edge where output tokens cost 5.0x less, and where what matters is LMArena Text: software and IT or LMArena Text: hard prompts, where it leads.

Model AGPT-5OpenAI38.8/1003 independent benchmarks$0.39 per solved taskModel BMistral Medium 3.1Mistral AINot benchmarkedNo coding benchmarkNo cost per solved task
Shared results
72
GPT-5 only
37
Mistral Medium 3.1 only
2
Like-for-like categories
8 of 9

Shared results can support a head-to-head reading. Results only one model has describe coverage, not superiority.

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 Medium 3.1 not benchmarked.
Widest category
Agentic work, 45.9 points apart on average over 1 shared benchmark.
Widest single gap
AA Math Index: GPT-5 94.3 against Mistral Medium 3.1 38.3, 56.0 points apart on a 0 to 100 scale.
Output price
GPT-5 $10.00 against Mistral Medium 3.1 $2.00 per million output tokens, 5.0x apart.
Context window
GPT-5 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-5BarsMistral Medium 3.1Ties
Coding61
Intelligence10
Agentic work10
Reasoning62
Math52
Knowledge74
Web design71
General1514
All shared boards4824
CodingLike-for-likeSix of these boards feed the Vibe Coding Index61
Coding benchmarks for GPT-5 and Mistral Medium 3.1
BenchmarkGPT-5Mistral Medium 3.1Leader
Aider polyglot88.0%Not measuredOnly GPT-5 measured
SWE-bench Verified74.4%Not measuredOnly GPT-5 measured
LMArena WebDev1418Not measuredOnly GPT-5 measured
AA Coding Index37.820.5GPT-5
LiveCodeBench (Vals AI)85.9%44.8%GPT-5
SWE-bench Verified (Vals AI)69.0%Not measuredOnly GPT-5 measured
Vibe Code Bench (Vals AI)20.1%Not measuredOnly GPT-5 measured
LiveCodeBench (Artificial Analysis run)84.6%40.6%GPT-5
SciCodeNot measured32.4%Only Mistral Medium 3.1 measured
Terminal-Bench Hard (Artificial Analysis run)37.9%10.6%GPT-5
Terminal-Bench49.6%Not measuredOnly GPT-5 measured
GSO-Bench6.9%Not measuredOnly GPT-5 measured
WeirdML60.7%Not measuredOnly GPT-5 measured
ALE-Bench807.6210.2GPT-5
LMArena Text: coding14361433GPT-5
LMArena Text: software and IT14201436Mistral Medium 3.1
LMArena WebDev: HTML1427Not measuredOnly GPT-5 measured
Neither model has a result on the other 21 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index10
Intelligence benchmarks for GPT-5 and Mistral Medium 3.1
BenchmarkGPT-5Mistral Medium 3.1Leader
AA Intelligence Index23.09.2GPT-5
Epoch Capabilities Index150.0Not measuredOnly GPT-5 measured
Agentic workLike-for-likePublic boards, shown as published, kept out of the index10
Agentic work benchmarks for GPT-5 and Mistral Medium 3.1
BenchmarkGPT-5Mistral Medium 3.1Leader
AA Agentic IndexNot measured1.9Only Mistral Medium 3.1 measured
τ²-Bench Telecom86.5%40.6%GPT-5
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
Neither model has a result on the other 32 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index62
Reasoning benchmarks for GPT-5 and Mistral Medium 3.1
BenchmarkGPT-5Mistral Medium 3.1Leader
GPQA Diamond85.6%Not measuredOnly GPT-5 measured
MMMU Pro (Vals AI)81.5%63.0%GPT-5
GPQA Diamond (Artificial Analysis run)85.4%58.8%GPT-5
Humanity's Last Exam (Artificial Analysis run)28.5%4.7%GPT-5
GPQA Diamond (Epoch AI run)86.2%Not measuredOnly GPT-5 measured
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%Not measuredOnly GPT-5 measured
Mystery game puzzles23.0%Not measuredOnly GPT-5 measured
EBR-bench12.7%Not measuredOnly GPT-5 measured
VPCT66.0%Not measuredOnly GPT-5 measured
LMArena Text: hard prompts14151426Mistral Medium 3.1
LMArena Text: expert14191408GPT-5
LMArena Text: hard prompts in English14191435Mistral Medium 3.1
LMArena Vision: diagrams12521175GPT-5
LMArena Vision: homework12781165GPT-5
Neither model has a result on the other 4 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index52
Math benchmarks for GPT-5 and Mistral Medium 3.1
BenchmarkGPT-5Mistral Medium 3.1Leader
AIME93.4%42.3%GPT-5
MATH 500 (Vals AI)96.0%87.0%GPT-5
MGSM (Vals AI)92.8%90.9%GPT-5
AA Math Index94.338.3GPT-5
AIME 2025 (Artificial Analysis run)94.3%38.3%GPT-5
OTIS Mock AIME91.4%Not measuredOnly GPT-5 measured
FrontierMath, tiers 1 to 355.4%Not measuredOnly GPT-5 measured
FrontierMath, tier 422.0%Not measuredOnly GPT-5 measured
ProofBench18.0%Not measuredOnly GPT-5 measured
MATH level 598.1%Not measuredOnly GPT-5 measured
LMArena Text: math14071408Mistral Medium 3.1
LMArena Text: mathematical work14051412Mistral Medium 3.1
Neither model has a result on the other 1 board here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index74
Knowledge benchmarks for GPT-5 and Mistral Medium 3.1
BenchmarkGPT-5Mistral Medium 3.1Leader
MMLU Pro86.5%75.3%GPT-5
LegalBench (Vals AI)86.0%62.0%GPT-5
CaseLaw (Vals AI)66.5%Not measuredOnly GPT-5 measured
CorpFin (Vals AI)61.1%50.7%GPT-5
TaxEval (Vals AI)73.4%70.3%GPT-5
MortgageTax (Vals AI)65.5%36.5%GPT-5
MedQA (Vals AI)96.3%78.2%GPT-5
MedCode (Vals AI)49.6%Not measuredOnly GPT-5 measured
MMLU Pro (Artificial Analysis run)87.1%68.3%GPT-5
SimpleQA Verified50.1%Not measuredOnly GPT-5 measured
GeoBench81.0%Not measuredOnly GPT-5 measured
LMArena Text: science14161444Mistral Medium 3.1
LMArena Text: medicine and healthcare14131449Mistral Medium 3.1
LMArena Text: legal and government14311439Mistral Medium 3.1
LMArena Text: business and finance14001418Mistral Medium 3.1
Neither model has a result on the other 2 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index71
Web design benchmarks for GPT-5 and Mistral Medium 3.1
BenchmarkGPT-5Mistral Medium 3.1Leader
Design Arena: websites11851133GPT-5
Design Arena: UI components11801099GPT-5
Design Arena: game dev11851074GPT-5
Design Arena: data viz12211144GPT-5
Design Arena: 3D10561081Mistral Medium 3.1
Design Arena: all code categories11681120GPT-5
Design Arena: SVG1189993GPT-5
Design Arena: ASCII art1140997GPT-5
Neither model has a result on the other 1 board here
GeneralLike-for-likePublic boards, shown as published, kept out of the index1514
General benchmarks for GPT-5 and Mistral Medium 3.1
BenchmarkGPT-5Mistral Medium 3.1Leader
SAGE (Vals AI)43.7%Not measuredOnly GPT-5 measured
MedScribe (Vals AI)83.7%Not measuredOnly GPT-5 measured
IFBench73.1%39.8%GPT-5
Long context reasoning (AA-LCR)78.2%42.7%GPT-5
DTBench90.7%67.5%GPT-5
LMCA40.0%19.1%GPT-5
Fiction.LiveBench97.2%Not measuredOnly GPT-5 measured
Creative writing (Lech Mazur)86.0%Not measuredOnly GPT-5 measured
LMArena Text14061424Mistral Medium 3.1
LMArena Text: instruction following13881398Mistral Medium 3.1
LMArena Text: creative writing13651391Mistral Medium 3.1
LMArena Vision12321172GPT-5
LMArena Text: English14091438Mistral Medium 3.1
LMArena Text: non-English13971408Mistral Medium 3.1
LMArena Text: Chinese14221447Mistral Medium 3.1
LMArena Text: German14161432Mistral Medium 3.1
LMArena Text: Japanese14091379GPT-5
LMArena Text: Korean13601380Mistral Medium 3.1
LMArena Text: French14091460Mistral Medium 3.1
LMArena Text: Spanish13991433Mistral Medium 3.1
LMArena Text: Russian14071411Mistral Medium 3.1
LMArena Text: Polish14311430GPT-5
LMArena Text: multi-turn14261418GPT-5
LMArena Text: longer queries13991406Mistral Medium 3.1
LMArena Text: writing and language13841395Mistral Medium 3.1
LMArena Text: entertainment and media13791390Mistral Medium 3.1
LMArena Vision: English12311179GPT-5
LMArena Vision: Chinese12671190GPT-5
LMArena Vision: reading text12461175GPT-5
LMArena Vision: humor12191168GPT-5
LMArena Vision: captioning12121145GPT-5
LMArena Vision: recognizing things12631147GPT-5
LMArena Vision: creative writing12101200GPT-5
Neither model has a result on the other 13 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 Medium 3.1
BenchmarkGPT-5Mistral 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$0.0063Fits 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-5$0.092Fits 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-5$0.350Fits 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-5 and Mistral Medium 3.1
SpecificationOpenAI GPT-5Mistral Medium 3.1
MakerOpenAIMistral AI
WeightsNo public weights listedNo public weights listed
ReleasedAugust 7, 2025August 13, 2025
Context window400K131K
Input $/Mtok$1.25$0.40
Output $/Mtok$10.00$2.00
Coding index38.8Not benchmarked
Independent measurements behind it30
Cost per solved task$0.39Not computable
SourceOpenRouter listingOpenRouter listing

Questions

Is GPT-5 better than Mistral Medium 3.1 for coding?

Only GPT-5 has a coding score, 38.8 on the Vibe Coding Index; Mistral Medium 3.1 has none, so the two cannot be ranked on coding. Mistral Medium 3.1 has the edge where output tokens cost 5.0x less, and where what matters is LMArena Text: software and IT or LMArena Text: hard prompts, where it leads.

Which is cheaper, GPT-5 or Mistral Medium 3.1?

GPT-5 costs $1.25 per million input tokens and $10.00 per million output tokens; Mistral Medium 3.1 costs $0.40 and $2.00. Cost per solved task is known for GPT-5 only.

Which has the bigger context window, GPT-5 or Mistral Medium 3.1?

GPT-5, with 400K tokens against 131K.

How many benchmarks is the GPT-5 vs Mistral Medium 3.1 comparison based on?

72 benchmarks have a result for both models as of October 21, 2026. GPT-5's coding index rests on 3 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