Enter opens the highlighted result. Esc closes.

Command A vs Mistral Medium 3.1

Updated October 21, 2026. 53 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.

Replace Command A Replace Mistral Medium 3.1
Command ACohere
Coding
No data
Overall
13.1
Output $/M
$10.00
12
Mistral Medium 3.1Mistral AI
Coding
No data
Overall
9.2
Output $/M
$2.00
41
vs boards won of 53 shared

Decision reading

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

Command A has the edge where the context window is larger, 256K against 131K tokens, and where what matters is LiveCodeBench (Vals AI) or LiveCodeBench (Artificial Analysis run), where it leads.

Model ACommand ACohereNot benchmarked1 independent benchmark$2.69 per solved taskModel BMistral Medium 3.1Mistral AINot benchmarkedNo coding benchmarkNo cost per solved task
Shared results
53
Command A only
7
Mistral Medium 3.1 only
21
Like-for-like categories
7 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
Command A not benchmarked, Mistral Medium 3.1 not benchmarked.
Widest category
Agentic work, 20.5 points apart on average over 2 shared benchmarks.
Widest single gap
τ²-Bench Telecom: Command A 80.7% against Mistral Medium 3.1 40.6%, 40.1 points apart on a 0 to 100 scale.
Output price
Command A $10.00 against Mistral Medium 3.1 $2.00 per million output tokens, 5.0x apart.
Context window
Command A takes 256K 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
CategoryCommand ABarsMistral Medium 3.1Ties
Coding34
Intelligence10
Agentic work11
Reasoning23
Math07
Knowledge37
General219
All shared boards1241
CodingLike-for-likeSix of these boards feed the Vibe Coding Index34
Coding benchmarks for Command A and Mistral Medium 3.1
BenchmarkCommand AMistral Medium 3.1Leader
AA Coding Index27.820.5Command A
LiveCodeBench (Vals AI)35.1%44.8%Mistral Medium 3.1
SWE-bench Verified (Vals AI)7.8%Not measuredOnly Command A measured
Terminal-Bench 2.1 (Vals AI)17.6%Not measuredOnly Command A measured
LiveCodeBench (Artificial Analysis run)28.7%40.6%Mistral Medium 3.1
SciCode38.5%32.4%Command A
Terminal-Bench Hard (Artificial Analysis run)25.0%10.6%Command A
ALE-BenchNot measured210.2Only Mistral Medium 3.1 measured
LMArena Text: coding13301433Mistral Medium 3.1
LMArena Text: software and IT13361436Mistral Medium 3.1
Neither model has a result on the other 28 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index10
Intelligence benchmarks for Command A and Mistral Medium 3.1
BenchmarkCommand AMistral Medium 3.1Leader
AA Intelligence Index13.19.2Command A
Neither model has a result on the other 1 board here
Agentic workLike-for-likePublic boards, shown as published, kept out of the index11
Agentic work benchmarks for Command A and Mistral Medium 3.1
BenchmarkCommand AMistral Medium 3.1Leader
AA Agentic Index1.01.9Mistral Medium 3.1
Finance Agent (Vals AI)9.0%Not measuredOnly Command A measured
τ²-Bench Telecom80.7%40.6%Command A
Neither model has a result on the other 36 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index23
Reasoning benchmarks for Command A and Mistral Medium 3.1
BenchmarkCommand AMistral Medium 3.1Leader
GPQA Diamond48.5%Not measuredOnly Command A measured
MMMU Pro (Vals AI)Not measured63.0%Only Mistral Medium 3.1 measured
GPQA Diamond (Artificial Analysis run)76.1%58.8%Command A
Humanity's Last Exam (Artificial Analysis run)12.0%4.7%Command A
LMArena Text: hard prompts13261426Mistral Medium 3.1
LMArena Text: expert12961408Mistral Medium 3.1
LMArena Text: hard prompts in English13351435Mistral Medium 3.1
LMArena Vision: diagramsNot measured1175Only Mistral Medium 3.1 measured
LMArena Vision: homeworkNot measured1165Only Mistral Medium 3.1 measured
Neither model has a result on the other 12 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index07
Math benchmarks for Command A and Mistral Medium 3.1
BenchmarkCommand AMistral Medium 3.1Leader
AIME13.3%42.3%Mistral Medium 3.1
MATH 500 (Vals AI)76.2%87.0%Mistral Medium 3.1
MGSM (Vals AI)85.7%90.9%Mistral Medium 3.1
AA Math Index13.038.3Mistral Medium 3.1
AIME 2025 (Artificial Analysis run)13.0%38.3%Mistral Medium 3.1
LMArena Text: math13001408Mistral Medium 3.1
LMArena Text: mathematical work13121412Mistral Medium 3.1
Neither model has a result on the other 6 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index37
Knowledge benchmarks for Command A and Mistral Medium 3.1
BenchmarkCommand AMistral Medium 3.1Leader
MMLU Pro69.2%75.3%Mistral Medium 3.1
LegalBench (Vals AI)79.7%62.0%Command A
CaseLaw (Vals AI)64.5%Not measuredOnly Command A measured
CorpFin (Vals AI)46.0%50.7%Mistral Medium 3.1
TaxEval (Vals AI)61.4%70.3%Mistral Medium 3.1
MortgageTax (Vals AI)Not measured36.5%Only Mistral Medium 3.1 measured
MedQA (Vals AI)80.5%78.2%Command A
MedCode (Vals AI)19.7%Not measuredOnly Command A measured
MMLU Pro (Artificial Analysis run)71.2%68.3%Command A
LMArena Text: science13391444Mistral Medium 3.1
LMArena Text: medicine and healthcare13341449Mistral Medium 3.1
LMArena Text: legal and government13481439Mistral Medium 3.1
LMArena Text: business and finance13151418Mistral 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 Command A and Mistral Medium 3.1
BenchmarkCommand AMistral Medium 3.1Leader
Design Arena: websitesNot measured1133Only Mistral Medium 3.1 measured
Design Arena: UI componentsNot measured1099Only Mistral Medium 3.1 measured
Design Arena: game devNot measured1074Only 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 measured993Only 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 index219
General benchmarks for Command A and Mistral Medium 3.1
BenchmarkCommand AMistral Medium 3.1Leader
MedScribe (Vals AI)55.7%Not measuredOnly Command A measured
IFBench73.9%39.8%Command A
Long context reasoning (AA-LCR)52.7%42.7%Command A
DTBench61.3%67.5%Mistral Medium 3.1
LMCA10.3%19.1%Mistral Medium 3.1
LMArena Text13311424Mistral Medium 3.1
LMArena Text: instruction following13091398Mistral Medium 3.1
LMArena Text: creative writing13191391Mistral Medium 3.1
LMArena VisionNot measured1172Only Mistral Medium 3.1 measured
LMArena Text: English13441438Mistral Medium 3.1
LMArena Text: non-English13131408Mistral Medium 3.1
LMArena Text: Chinese13271447Mistral Medium 3.1
LMArena Text: German13421432Mistral Medium 3.1
LMArena Text: Japanese12851379Mistral Medium 3.1
LMArena Text: Korean12851380Mistral Medium 3.1
LMArena Text: French13511460Mistral Medium 3.1
LMArena Text: Spanish13471433Mistral Medium 3.1
LMArena Text: Russian13141411Mistral Medium 3.1
LMArena Text: Polish13241430Mistral Medium 3.1
LMArena Text: multi-turn13381418Mistral Medium 3.1
LMArena Text: longer queries13341406Mistral Medium 3.1
LMArena Text: writing and language13281395Mistral Medium 3.1
LMArena Text: entertainment and media13061390Mistral Medium 3.1
LMArena Vision: EnglishNot measured1179Only Mistral Medium 3.1 measured
LMArena Vision: ChineseNot measured1190Only Mistral Medium 3.1 measured
LMArena Vision: reading textNot measured1175Only Mistral Medium 3.1 measured
LMArena Vision: humorNot measured1168Only Mistral Medium 3.1 measured
LMArena Vision: captioningNot measured1145Only Mistral Medium 3.1 measured
LMArena Vision: recognizing thingsNot measured1147Only Mistral Medium 3.1 measured
LMArena Vision: creative writingNot measured1200Only Mistral Medium 3.1 measured
Neither model has a result on the other 16 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for Command A and Mistral Medium 3.1
BenchmarkCommand AMistral 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

Command A$0.0075Fits 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

Command A$0.155Fits 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

Command A$0.600Fits 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 Command A and Mistral Medium 3.1
SpecificationCohere Command AMistral Medium 3.1
MakerCohereMistral AI
WeightsOpen weightsNo public weights listed
ReleasedMarch 13, 2025August 13, 2025
Context window256K131K
Input $/Mtok$2.50$0.40
Output $/Mtok$10.00$2.00
Coding indexNot benchmarkedNot benchmarked
Independent measurements behind it10
Cost per solved task$2.69Not computable
SourceOpenRouter listingOpenRouter listing

Questions

Is Command A better than Mistral Medium 3.1 for coding?

Neither model has a coding score yet, so the two cannot be ranked on coding. Command A has the edge where the context window is larger, 256K against 131K tokens, and where what matters is LiveCodeBench (Vals AI) or LiveCodeBench (Artificial Analysis run), where it leads.

Which is cheaper, Command A or Mistral Medium 3.1?

Command A costs $2.50 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 Command A only.

Which has the bigger context window, Command A or Mistral Medium 3.1?

Command A, with 256K tokens against 131K.

How many benchmarks is the Command A vs Mistral Medium 3.1 comparison based on?

53 benchmarks have a result for both models as of October 21, 2026. Command A's coding index rests on 1 independent benchmark 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