Enter opens the highlighted result. Esc closes.

Command A vs DeepSeek V4 Pro 0423

Updated October 21, 2026. 45 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 DeepSeek V4 Pro 0423
Command ACohere
Coding
No data
Overall
13.1
Output $/M
$10.00
1
DeepSeek V4 Pro 0423DeepSeek
Coding
38.7
Overall
30.4
Output $/M
$2.716
44
vs boards won of 45 shared

Decision reading

Only DeepSeek V4 Pro 0423 has a coding score, 38.7 on the Vibe Coding Index; Command A has none, so the two cannot be ranked on coding.

Command A has the edge where the benchmark that matters is CaseLaw (Vals AI), where it leads.

Model ACommand ACohereNot benchmarked1 independent benchmark$2.69 per solved taskModel BDeepSeek V4 Pro 0423DeepSeek38.7/1005 independent benchmarks$0.57 per solved task
Shared results
45
Command A only
15
DeepSeek V4 Pro 0423 only
38
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, DeepSeek V4 Pro 0423 38.7 from 5 benchmarks.
Widest category
Coding, 38.6 points apart on average over 6 shared benchmarks.
Widest single gap
SWE-bench Verified (Vals AI): Command A 7.8% against DeepSeek V4 Pro 0423 77.4%, 69.6 points apart on a 0 to 100 scale.
Output price
Command A $10.00 against DeepSeek V4 Pro 0423 $2.716 per million output tokens, 3.7x apart.
Context window
Command A takes 256K tokens, DeepSeek V4 Pro 0423 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
CategoryCommand ABarsDeepSeek V4 Pro 0423Ties
Coding06
Intelligence01
Agentic work02
Reasoning04
Math02
Knowledge19
General020
All shared boards144
CodingLike-for-likeSix of these boards feed the Vibe Coding Index06
Coding benchmarks for Command A and DeepSeek V4 Pro 0423
BenchmarkCommand ADeepSeek V4 Pro 0423Leader
LMArena WebDevNot measured1447Only DeepSeek V4 Pro 0423 measured
AA Coding Index27.859.4DeepSeek V4 Pro 0423
LiveCodeBench (Vals AI)35.1%87.5%DeepSeek V4 Pro 0423
SWE-bench Verified (Vals AI)7.8%77.4%DeepSeek V4 Pro 0423
Terminal-Bench 4 (Vals AI)Not measured11.1%Only DeepSeek V4 Pro 0423 measured
Vibe Code Bench (Vals AI)Not measured49.9%Only DeepSeek V4 Pro 0423 measured
Code migration (Vals AI)Not measured26.2%Only DeepSeek V4 Pro 0423 measured
ProgramBench (Vals AI)Not measured0.0%Only DeepSeek V4 Pro 0423 measured
Terminal-Bench 2.1 (Vals AI)17.6%50.2%DeepSeek V4 Pro 0423
SkillsBench (Vals AI)Not measured51.3%Only DeepSeek V4 Pro 0423 measured
LiveCodeBench (Artificial Analysis run)28.7%Not measuredOnly Command A measured
SciCode38.5%Not measuredOnly Command A measured
Terminal-Bench Hard (Artificial Analysis run)25.0%Not measuredOnly Command A measured
FrontierCodeNot measured17.6%Only DeepSeek V4 Pro 0423 measured
WeirdMLNot measured48.9%Only DeepSeek V4 Pro 0423 measured
ALE-BenchNot measured1006.1Only DeepSeek V4 Pro 0423 measured
LMArena Text: coding13301470DeepSeek V4 Pro 0423
LMArena Text: software and IT13361469DeepSeek V4 Pro 0423
LMArena WebDev: ReactNot measured1441Only DeepSeek V4 Pro 0423 measured
LMArena WebDev: HTMLNot measured1435Only DeepSeek V4 Pro 0423 measured
Neither model has a result on the other 18 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
Intelligence benchmarks for Command A and DeepSeek V4 Pro 0423
BenchmarkCommand ADeepSeek V4 Pro 0423Leader
AA Intelligence Index13.130.4DeepSeek V4 Pro 0423
Epoch Capabilities IndexNot measured149.1Only DeepSeek V4 Pro 0423 measured
Agentic workLike-for-likePublic boards, shown as published, kept out of the index02
Agentic work benchmarks for Command A and DeepSeek V4 Pro 0423
BenchmarkCommand ADeepSeek V4 Pro 0423Leader
AA Agentic Index1.026.3DeepSeek V4 Pro 0423
Design Arena: agents building web appsNot measured1000Only DeepSeek V4 Pro 0423 measured
Design Arena: agents building full-stack appsNot measured948Only DeepSeek V4 Pro 0423 measured
Design Arena: agents building Godot gamesNot measured1059Only DeepSeek V4 Pro 0423 measured
Finance Agent (Vals AI)9.0%44.1%DeepSeek V4 Pro 0423
Tax Agent Bench (Vals AI)Not measured25.2%Only DeepSeek V4 Pro 0423 measured
Legal Research Bench (Vals AI)Not measured23.1%Only DeepSeek V4 Pro 0423 measured
Excel Modeling Benchmark (Vals AI)Not measured51.6%Only DeepSeek V4 Pro 0423 measured
τ²-Bench Telecom80.7%Not measuredOnly Command A measured
Vending-Bench 2Not measured$3,285Only DeepSeek V4 Pro 0423 measured
Neither model has a result on the other 29 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index04
Reasoning benchmarks for Command A and DeepSeek V4 Pro 0423
BenchmarkCommand ADeepSeek V4 Pro 0423Leader
GPQA Diamond48.5%89.4%DeepSeek V4 Pro 0423
GPQA Diamond (Artificial Analysis run)76.1%Not measuredOnly Command A measured
Humanity's Last Exam (Artificial Analysis run)12.0%Not measuredOnly Command A measured
GPQA Diamond (Epoch AI run)Not measured90.9%Only DeepSeek V4 Pro 0423 measured
Chess puzzlesNot measured19.0%Only DeepSeek V4 Pro 0423 measured
Mystery game puzzlesNot measured17.0%Only DeepSeek V4 Pro 0423 measured
LMArena Text: hard prompts13261461DeepSeek V4 Pro 0423
LMArena Text: expert12961463DeepSeek V4 Pro 0423
LMArena Text: hard prompts in English13351466DeepSeek V4 Pro 0423
Neither model has a result on the other 12 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index02
Math benchmarks for Command A and DeepSeek V4 Pro 0423
BenchmarkCommand ADeepSeek V4 Pro 0423Leader
AIME13.3%Not measuredOnly Command A measured
MATH 500 (Vals AI)76.2%Not measuredOnly Command A measured
MGSM (Vals AI)85.7%Not measuredOnly Command A measured
AA Math Index13.0Not measuredOnly Command A measured
AIME 2025 (Artificial Analysis run)13.0%Not measuredOnly Command A measured
OTIS Mock AIMENot measured96.7%Only DeepSeek V4 Pro 0423 measured
FrontierMath, tiers 1 to 3Not measured45.3%Only DeepSeek V4 Pro 0423 measured
FrontierMath, tier 4Not measured2.4%Only DeepSeek V4 Pro 0423 measured
ProofBenchNot measured16.0%Only DeepSeek V4 Pro 0423 measured
LMArena Text: math13001443DeepSeek V4 Pro 0423
LMArena Text: mathematical work13121455DeepSeek V4 Pro 0423
Neither model has a result on the other 2 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index19
Knowledge benchmarks for Command A and DeepSeek V4 Pro 0423
BenchmarkCommand ADeepSeek V4 Pro 0423Leader
MMLU Pro69.2%87.3%DeepSeek V4 Pro 0423
LegalBench (Vals AI)79.7%80.3%DeepSeek V4 Pro 0423
CaseLaw (Vals AI)64.5%59.4%Command A
CorpFin (Vals AI)46.0%61.4%DeepSeek V4 Pro 0423
TaxEval (Vals AI)61.4%72.1%DeepSeek V4 Pro 0423
MedQA (Vals AI)80.5%Not measuredOnly Command A measured
MedCode (Vals AI)19.7%40.5%DeepSeek V4 Pro 0423
MMLU Pro (Artificial Analysis run)71.2%Not measuredOnly Command A measured
SimpleQA VerifiedNot measured47.0%Only DeepSeek V4 Pro 0423 measured
LMArena Text: science13391470DeepSeek V4 Pro 0423
LMArena Text: medicine and healthcare13341466DeepSeek V4 Pro 0423
LMArena Text: legal and government13481464DeepSeek V4 Pro 0423
LMArena Text: business and finance13151443DeepSeek V4 Pro 0423
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 DeepSeek V4 Pro 0423
BenchmarkCommand ADeepSeek V4 Pro 0423Leader
Design Arena: websitesNot measured1235Only DeepSeek V4 Pro 0423 measured
Design Arena: UI componentsNot measured1222Only DeepSeek V4 Pro 0423 measured
Design Arena: game devNot measured1229Only DeepSeek V4 Pro 0423 measured
Design Arena: data vizNot measured1202Only DeepSeek V4 Pro 0423 measured
Design Arena: 3DNot measured1254Only DeepSeek V4 Pro 0423 measured
Design Arena: all code categoriesNot measured1240Only DeepSeek V4 Pro 0423 measured
Design Arena: SVGNot measured1140Only DeepSeek V4 Pro 0423 measured
Design Arena: ASCII artNot measured1148Only DeepSeek V4 Pro 0423 measured
Neither model has a result on the other 1 board here
GeneralLike-for-likePublic boards, shown as published, kept out of the index020
General benchmarks for Command A and DeepSeek V4 Pro 0423
BenchmarkCommand ADeepSeek V4 Pro 0423Leader
Public Benefits Bench (Vals AI)Not measured62.9%Only DeepSeek V4 Pro 0423 measured
MedScribe (Vals AI)55.7%75.1%DeepSeek V4 Pro 0423
IFBench73.9%Not measuredOnly Command A measured
Long context reasoning (AA-LCR)52.7%Not measuredOnly Command A measured
DTBench61.3%90.7%DeepSeek V4 Pro 0423
LMCA10.3%41.2%DeepSeek V4 Pro 0423
Surface Evolver BenchNot measured40.0%Only DeepSeek V4 Pro 0423 measured
CL-bench LifeNot measured13.5%Only DeepSeek V4 Pro 0423 measured
LMArena Text13311451DeepSeek V4 Pro 0423
LMArena Text: instruction following13091445DeepSeek V4 Pro 0423
LMArena Text: creative writing13191446DeepSeek V4 Pro 0423
LMArena Text: English13441459DeepSeek V4 Pro 0423
LMArena Text: non-English13131439DeepSeek V4 Pro 0423
LMArena Text: Chinese13271481DeepSeek V4 Pro 0423
LMArena Text: German13421458DeepSeek V4 Pro 0423
LMArena Text: Japanese12851446DeepSeek V4 Pro 0423
LMArena Text: Korean12851409DeepSeek V4 Pro 0423
LMArena Text: French13511473DeepSeek V4 Pro 0423
LMArena Text: Spanish13471457DeepSeek V4 Pro 0423
LMArena Text: Russian13141453DeepSeek V4 Pro 0423
LMArena Text: Polish13241461DeepSeek V4 Pro 0423
LMArena Text: multi-turn13381468DeepSeek V4 Pro 0423
LMArena Text: longer queries13341458DeepSeek V4 Pro 0423
LMArena Text: writing and language13281447DeepSeek V4 Pro 0423
LMArena Text: entertainment and media13061431DeepSeek V4 Pro 0423
Neither model has a result on the other 21 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for Command A and DeepSeek V4 Pro 0423
BenchmarkCommand ADeepSeek V4 Pro 0423Leader
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
DeepSeek V4 Pro 0423$0.0026Fits in one request

DeepSeek V4 Pro 0423 costs less

Repository review

50K input + 3K output tokens

Command A$0.155Fits in one request
DeepSeek V4 Pro 0423$0.069Fits in one request

DeepSeek V4 Pro 0423 costs less

Agent loop

200K input + 10K output tokens

Command A$0.600Fits in one request
DeepSeek V4 Pro 0423$0.272Fits in one request

DeepSeek V4 Pro 0423 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 DeepSeek V4 Pro 0423
SpecificationCohere Command ADeepSeek V4 Pro 0423
MakerCohereDeepSeek
WeightsOpen weightsOpen weights
ReleasedMarch 13, 2025April 24, 2026
Context window256K1.05M
Input $/Mtok$2.50$1.225
Output $/Mtok$10.00$2.716
Coding indexNot benchmarked38.7
Independent measurements behind it15
Cost per solved task$2.69$0.57
SourceOpenRouter listingOpenRouter listing

Questions

Is Command A better than DeepSeek V4 Pro 0423 for coding?

Only DeepSeek V4 Pro 0423 has a coding score, 38.7 on the Vibe Coding Index; Command A has none, so the two cannot be ranked on coding. Command A has the edge where the benchmark that matters is CaseLaw (Vals AI), where it leads.

Which is cheaper, Command A or DeepSeek V4 Pro 0423?

Command A costs $2.50 per million input tokens and $10.00 per million output tokens; DeepSeek V4 Pro 0423 costs $1.225 and $2.716. Per solved SWE-bench Verified task, Command A costs $2.69 and DeepSeek V4 Pro 0423 $0.57.

Which has the bigger context window, Command A or DeepSeek V4 Pro 0423?

DeepSeek V4 Pro 0423, with 1.05M tokens against 256K.

How many benchmarks is the Command A vs DeepSeek V4 Pro 0423 comparison based on?

45 benchmarks have a result for both models as of October 21, 2026. Command A's coding index rests on 1 independent benchmark and DeepSeek V4 Pro 0423's on 5. Where only one model has a result, the page says so instead of naming a winner.

Compare next