Enter opens the highlighted result. Esc closes.

DeepSeek V3.2 Exp vs Mistral Medium 3

Updated October 21, 2026. 47 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.

Replace DeepSeek V3.2 Exp Replace Mistral Medium 3
DeepSeek V3.2 ExpDeepSeek
Coding
No data
Overall
16.6
Output $/M
$0.41
47
Mistral Medium 3Mistral AI
Coding
No data
Overall
9.0
Output $/M
$2.00
0
vs boards won of 47 shared

Decision reading

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

DeepSeek V3.2 Exp has the edge where output tokens cost 4.9x less, and where the context window is larger, 164K against 131K tokens.

Model ADeepSeek V3.2 ExpDeepSeekNot benchmarked1 independent benchmarkNo cost per solved taskModel BMistral Medium 3Mistral AINot benchmarkedNo coding benchmarkNo cost per solved task
Shared results
47
DeepSeek V3.2 Exp only
10
Mistral Medium 3 only
10
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
DeepSeek V3.2 Exp not benchmarked, Mistral Medium 3 not benchmarked.
Widest category
Math, 34.9 points apart on average over 4 shared benchmarks.
Widest single gap
AA Math Index: DeepSeek V3.2 Exp 87.7 against Mistral Medium 3 30.3, 57.4 points apart on a 0 to 100 scale.
Output price
DeepSeek V3.2 Exp $0.41 against Mistral Medium 3 $2.00 per million output tokens, 4.9x apart.
Context window
DeepSeek V3.2 Exp takes 164K tokens, Mistral Medium 3 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
CategoryDeepSeek V3.2 ExpBarsMistral Medium 3Ties
Coding40
Intelligence20
Agentic work10
Reasoning50
Math40
Knowledge50
Web design60
General200
All shared boards470
CodingLike-for-likeSix of these boards feed the Vibe Coding Index40
Coding benchmarks for DeepSeek V3.2 Exp and Mistral Medium 3
BenchmarkDeepSeek V3.2 ExpMistral Medium 3Leader
Aider polyglot74.2%Not measuredOnly DeepSeek V3.2 Exp measured
LMArena WebDev1272Not measuredOnly DeepSeek V3.2 Exp measured
LiveCodeBench (Artificial Analysis run)78.9%40.0%DeepSeek V3.2 Exp
Terminal-Bench Hard (Artificial Analysis run)31.1%3.8%DeepSeek V3.2 Exp
WeirdML39.5%Not measuredOnly DeepSeek V3.2 Exp measured
LMArena Text: coding14381385DeepSeek V3.2 Exp
LMArena Text: software and IT14381385DeepSeek V3.2 Exp
LMArena WebDev: HTML1281Not measuredOnly DeepSeek V3.2 Exp measured
Neither model has a result on the other 30 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
Intelligence benchmarks for DeepSeek V3.2 Exp and Mistral Medium 3
BenchmarkDeepSeek V3.2 ExpMistral Medium 3Leader
AA Intelligence Index16.69.0DeepSeek V3.2 Exp
Epoch Capabilities Index144.9134.0DeepSeek V3.2 Exp
Agentic workLike-for-likePublic boards, shown as published, kept out of the index10
Agentic work benchmarks for DeepSeek V3.2 Exp and Mistral Medium 3
BenchmarkDeepSeek V3.2 ExpMistral Medium 3Leader
τ²-Bench Telecom33.9%24.3%DeepSeek V3.2 Exp
TheAgentCompany42.9%Not measuredOnly DeepSeek V3.2 Exp measured
Neither model has a result on the other 37 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index50
Reasoning benchmarks for DeepSeek V3.2 Exp and Mistral Medium 3
BenchmarkDeepSeek V3.2 ExpMistral Medium 3Leader
GPQA Diamond (Artificial Analysis run)79.7%57.8%DeepSeek V3.2 Exp
Humanity's Last Exam (Artificial Analysis run)14.9%4.1%DeepSeek V3.2 Exp
LMArena Text: hard prompts14291364DeepSeek V3.2 Exp
LMArena Text: expert14221342DeepSeek V3.2 Exp
LMArena Text: hard prompts in English14441374DeepSeek V3.2 Exp
LMArena Vision: diagramsNot measured1155Only Mistral Medium 3 measured
LMArena Vision: homeworkNot measured1165Only Mistral Medium 3 measured
Neither model has a result on the other 14 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index40
Math benchmarks for DeepSeek V3.2 Exp and Mistral Medium 3
BenchmarkDeepSeek V3.2 ExpMistral Medium 3Leader
AA Math Index87.730.3DeepSeek V3.2 Exp
AIME 2025 (Artificial Analysis run)87.7%30.3%DeepSeek V3.2 Exp
LMArena Text: math14221353DeepSeek V3.2 Exp
LMArena Text: mathematical work14331354DeepSeek V3.2 Exp
Neither model has a result on the other 9 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index50
Knowledge benchmarks for DeepSeek V3.2 Exp and Mistral Medium 3
BenchmarkDeepSeek V3.2 ExpMistral Medium 3Leader
MMLU Pro (Artificial Analysis run)85.0%76.0%DeepSeek V3.2 Exp
LMArena Text: science14431381DeepSeek V3.2 Exp
LMArena Text: medicine and healthcare14681381DeepSeek V3.2 Exp
LMArena Text: legal and government14191384DeepSeek V3.2 Exp
LMArena Text: business and finance14121352DeepSeek V3.2 Exp
Neither model has a result on the other 12 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index60
Web design benchmarks for DeepSeek V3.2 Exp and Mistral Medium 3
BenchmarkDeepSeek V3.2 ExpMistral Medium 3Leader
Design Arena: websites11791079DeepSeek V3.2 Exp
Design Arena: UI components11671024DeepSeek V3.2 Exp
Design Arena: game dev11441018DeepSeek V3.2 Exp
Design Arena: data viz11521034DeepSeek V3.2 Exp
Design Arena: 3D11481083DeepSeek V3.2 Exp
Design Arena: all code categories11711069DeepSeek V3.2 Exp
Design Arena: SVG1032Not measuredOnly DeepSeek V3.2 Exp measured
Neither model has a result on the other 2 boards here
GeneralLike-for-likePublic boards, shown as published, kept out of the index200
General benchmarks for DeepSeek V3.2 Exp and Mistral Medium 3
BenchmarkDeepSeek V3.2 ExpMistral Medium 3Leader
IFBench54.1%39.3%DeepSeek V3.2 Exp
Long context reasoning (AA-LCR)72.3%31.3%DeepSeek V3.2 Exp
DTBench87.7%62.3%DeepSeek V3.2 Exp
LMCA29.1%Not measuredOnly DeepSeek V3.2 Exp measured
Fiction.LiveBench83.3%Not measuredOnly DeepSeek V3.2 Exp measured
CL-bench13.2%Not measuredOnly DeepSeek V3.2 Exp measured
CL-bench Life9.5%Not measuredOnly DeepSeek V3.2 Exp measured
LMArena Text14251370DeepSeek V3.2 Exp
LMArena Text: instruction following14011338DeepSeek V3.2 Exp
LMArena Text: creative writing14041343DeepSeek V3.2 Exp
LMArena VisionNot measured1157Only Mistral Medium 3 measured
LMArena Text: English14411385DeepSeek V3.2 Exp
LMArena Text: non-English14041353DeepSeek V3.2 Exp
LMArena Text: Chinese14611374DeepSeek V3.2 Exp
LMArena Text: German14401377DeepSeek V3.2 Exp
LMArena Text: Japanese13311316DeepSeek V3.2 Exp
LMArena Text: Korean13721304DeepSeek V3.2 Exp
LMArena Text: French14341368DeepSeek V3.2 Exp
LMArena Text: Spanish14411364DeepSeek V3.2 Exp
LMArena Text: Russian14121359DeepSeek V3.2 Exp
LMArena Text: Polish14351371DeepSeek V3.2 Exp
LMArena Text: multi-turn14221384DeepSeek V3.2 Exp
LMArena Text: longer queries14181360DeepSeek V3.2 Exp
LMArena Text: writing and language14071352DeepSeek V3.2 Exp
LMArena Text: entertainment and media14071335DeepSeek V3.2 Exp
LMArena Vision: EnglishNot measured1172Only Mistral Medium 3 measured
LMArena Vision: ChineseNot measured1161Only Mistral Medium 3 measured
LMArena Vision: reading textNot measured1154Only Mistral Medium 3 measured
LMArena Vision: humorNot measured1145Only Mistral Medium 3 measured
LMArena Vision: captioningNot measured1094Only Mistral Medium 3 measured
LMArena Vision: recognizing thingsNot measured1141Only Mistral Medium 3 measured
LMArena Vision: creative writingNot measured1146Only Mistral Medium 3 measured
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 DeepSeek V3.2 Exp and Mistral Medium 3
BenchmarkDeepSeek V3.2 ExpMistral Medium 3Leader
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

DeepSeek V3.2 Exp$0.0005Fits in one request
Mistral Medium 3$0.0014Fits in one request

DeepSeek V3.2 Exp costs less

Repository review

50K input + 3K output tokens

DeepSeek V3.2 Exp$0.015Fits in one request
Mistral Medium 3$0.026Fits in one request

DeepSeek V3.2 Exp costs less

Agent loop

200K input + 10K output tokens

DeepSeek V3.2 Exp$0.058Exceeds the context window
Mistral Medium 3$0.100Exceeds the context window

DeepSeek V3.2 Exp 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 DeepSeek V3.2 Exp and Mistral Medium 3
SpecificationDeepSeek V3.2 ExpMistral Medium 3
MakerDeepSeekMistral AI
WeightsOpen weightsNo public weights listed
ReleasedSeptember 29, 2025May 7, 2025
Context window164K131K
Input $/Mtok$0.27$0.40
Output $/Mtok$0.41$2.00
Coding indexNot benchmarkedNot benchmarked
Independent measurements behind it10
Cost per solved taskNot computableNot computable
SourceOpenRouter listingOpenRouter listing

Questions

Is DeepSeek V3.2 Exp better than Mistral Medium 3 for coding?

Neither model has a coding score yet, so the two cannot be ranked on coding. DeepSeek V3.2 Exp has the edge where output tokens cost 4.9x less, and where the context window is larger, 164K against 131K tokens.

Which is cheaper, DeepSeek V3.2 Exp or Mistral Medium 3?

DeepSeek V3.2 Exp costs $0.27 per million input tokens and $0.41 per million output tokens; Mistral Medium 3 costs $0.40 and $2.00. Cost per solved task is known for neither of them.

Which has the bigger context window, DeepSeek V3.2 Exp or Mistral Medium 3?

DeepSeek V3.2 Exp, with 164K tokens against 131K.

How many benchmarks is the DeepSeek V3.2 Exp vs Mistral Medium 3 comparison based on?

47 benchmarks have a result for both models as of October 21, 2026. DeepSeek V3.2 Exp's coding index rests on 1 independent benchmark and Mistral Medium 3's on 0. Where only one model has a result, the page says so instead of naming a winner.

Compare next