Model comparison

Command A vs DeepSeek-V3

DeepSeek-V3 is the stronger model overall, scoring 39.5 to 36.5 on the Noometry Index.

Last verified October 12, 2026. 23 shared benchmarks.

Command A

Cohere

36.5

Rank #215 Confirmed

DeepSeek-V3

DeepSeek

39.5

Rank #166 Confirmed

Summary

They share 23 benchmarks with published results for both. Command A scores higher in 2 categories and DeepSeek-V3 in 6 categories; 7 gaps are clear of the uncertainty.
The widest gap is in coding, where DeepSeek-V3 leads 42.3 to 27.2.
The biggest single-benchmark swing is Aider Polyglot: 12% for Command A and 55.1% for DeepSeek-V3.
DeepSeek-V3 is cheaper at $0.24 / $0.90 per million input/output tokens, against $2.50 / $10 for Command A.
Command A accepts more context: 256K tokens versus 164K.

Side by side

Command A and DeepSeek-V3 specifications
	Command A	DeepSeek-V3
Provider	Cohere	DeepSeek
Noometry Index	36.5	39.5
Released	2025-03-13	2024-12-26
Weights	Open	Open
Context window	256K	164K
Max output	8K	164K
Input $ / M tokens	$2.50	$0.24
Output $ / M tokens	$10	$0.90
Results tracked	24	60

Sponsored placements are available on pages like this one. Advertise on Noometry

Category by category

Coding DeepSeek-V3 leads

Command A: 27.2 (#322), DeepSeek-V3: 42.3 (#106)

Coding benchmarks
Benchmark	Command A	DeepSeek-V3
Aider Polyglot	12%	55.1%
LMArena Coding	1330	1368
SciCode	—	35.8%
WeirdML	—	36.1%
BigCodeBench Instruct	—	50%
LiveBench Coding	—	70.9%
BigCodeBench Complete	—	62.2%
HumanEval+	—	86.6%
MBPP+	—	73%

Agentic & Tool Use Not comparable

Command A: 35.9 (#40), DeepSeek-V3: —

Agentic & Tool Use benchmarks
Benchmark	Command A	DeepSeek-V3
Berkeley Function Calling Leaderboard	57.1%	—
METR Time Horizons	—	49.6%

Reasoning DeepSeek-V3 leads

Command A: 18.3 (#283), DeepSeek-V3: 20.5 (#236)

Reasoning benchmarks
Benchmark	Command A	DeepSeek-V3
Kagi LLM Benchmark	28.8%	52.3%
LMArena Hard Prompts	1326	1365
DTBench	61.3%	64.8%
LMCA	10.3%	15.5%
SimpleBench	—	27.2%
CritPt	—	0%
LiveBench Reasoning	—	65.8%
LiveBench Data Analysis	—	60.9%
BIG-Bench Hard	—	87.5%
Epoch Capabilities Index	—	135.94
ForecastBench	—	59.1
HellaSwag	—	88.9%
LiveBench	—	66.9%
PIQA	—	84.7%
WinoGrande	—	85.2%

Math Command A leads

Command A: 36.2 (#171), DeepSeek-V3: 32.1 (#219)

Math benchmarks
Benchmark	Command A	DeepSeek-V3
LMArena Math	1300	1373
OTIS Mock AIME 2024-2025	—	37.8%
Omni-MATH	—	40.3%
LiveBench Math	—	73.5%
MATH Level 5	—	75.5%
FrontierMath (Feb 2025 set)	—	1.7%

Knowledge Too close to call

Command A: 37.1 (#159), DeepSeek-V3: 37.5 (#155)

Knowledge benchmarks
Benchmark	Command A	DeepSeek-V3
Vectara Hallucination Rate	9.3%	6.1%
LMArena Expert	1295	1351
GPQA Diamond	—	67.6%
MMLU-Pro	—	72.3%
Confabulations	—	26.1%
GPQA (HELM)	—	53.8%
ARC (AI2) Challenge	—	95.3%
MMLU	—	87.2%
TriviaQA	—	82.9%

Multilingual DeepSeek-V3 leads

Command A: 45.3 (#170), DeepSeek-V3: 48.5 (#143)

Multilingual benchmarks
Benchmark	Command A	DeepSeek-V3
LMArena Non-English	1313	1358
LMArena Chinese	1327	1391
LMArena French	1351	1385
LMArena German	1341	1374
LMArena Japanese	1285	1333
LMArena Korean	1285	1319
LMArena Russian	1314	1373
LMArena Spanish	1347	1358

Instruction Following DeepSeek-V3 leads

Command A: 69.1 (#177), DeepSeek-V3: 72.8 (#130)

Instruction Following benchmarks
Benchmark	Command A	DeepSeek-V3
LMArena Instruction Following	1309	1345
LiveBench Instruction Following	—	81.5%
IFEval	—	83.2%

Long Context Command A leads

Command A: 40.6 (#151), DeepSeek-V3: 34.0 (#253)

Long Context benchmarks
Benchmark	Command A	DeepSeek-V3
LMArena Longer Query	1334	1352
Fiction.LiveBench	—	50%

Writing & Preference DeepSeek-V3 leads

Command A: 47.6 (#208), DeepSeek-V3: 57.4 (#130)

Writing & Preference benchmarks
Benchmark	Command A	DeepSeek-V3
LMArena Text	1331	1375
LMArena Creative Writing	1319	1364
EQ-Bench Creative Writing	1145	1472
LMArena Multi-Turn	1339	1389
Short-Story Creative Writing	—	77%
WildBench	—	83%
LiveBench Language	—	49.1%

Frequently asked questions

Is Command A better than DeepSeek-V3?

DeepSeek-V3 is the stronger model overall, scoring 39.5 to 36.5 on the Noometry Index.

Which is cheaper, Command A or DeepSeek-V3?

DeepSeek-V3 is cheaper. It lists at $0.24 per million input tokens and $0.90 per million output tokens; Command A lists at $2.50 and $10.

Is Command A or DeepSeek-V3 better for coding?

DeepSeek-V3 scores higher on coding benchmarks: 42.3 versus 27.2 in the Noometry coding category.

Which has the bigger context window?

Command A does, with 256K tokens against 164K.

How many benchmarks do Command A and DeepSeek-V3 share?

23 benchmarks have published results for both models. Command A has 24 scored results on Noometry and DeepSeek-V3 has 60.