Model comparison

Command A vs DeepSeek-V3.1

DeepSeek-V3.1 is the stronger model overall, scoring 42.8 to 36.5 on the Noometry Index.

Last verified October 10, 2026. 22 shared benchmarks.

Command A

Cohere

36.5

Rank #215 Confirmed

DeepSeek-V3.1

DeepSeek

42.8

Rank #108 Confirmed

Summary

They share 22 benchmarks with published results for both. Command A scores higher in 1 category and DeepSeek-V3.1 in 7 categories; 8 gaps are clear of the uncertainty.
The widest gap is in coding, where DeepSeek-V3.1 leads 40.3 to 27.2.
The biggest single-benchmark swing is Kagi LLM Benchmark: 28.8% for Command A and 53.2% for DeepSeek-V3.1.
DeepSeek-V3.1 is cheaper at $0.25 / $0.95 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-V3.1 specifications
	Command A	DeepSeek-V3.1
Provider	Cohere	DeepSeek
Noometry Index	36.5	42.8
Released	2025-03-13	2025-08-21
Weights	Open	Open
Context window	256K	164K
Max output	8K	8K
Input $ / M tokens	$2.50	$0.25
Output $ / M tokens	$10	$0.95
Results tracked	24	27

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

Category by category

Coding DeepSeek-V3.1 leads

Command A: 27.2 (#322), DeepSeek-V3.1: 40.3 (#144)

Coding benchmarks
Benchmark	Command A	DeepSeek-V3.1
LMArena Coding	1330	1417
Aider Polyglot	12%	—
WeirdML	—	38.4%

Agentic & Tool Use Not comparable

Command A: 35.9 (#40), DeepSeek-V3.1: —

Agentic & Tool Use benchmarks
Benchmark	Command A	DeepSeek-V3.1
Berkeley Function Calling Leaderboard	57.1%	—

Reasoning DeepSeek-V3.1 leads

Command A: 18.3 (#283), DeepSeek-V3.1: 27.9 (#110)

Reasoning benchmarks
Benchmark	Command A	DeepSeek-V3.1
Kagi LLM Benchmark	28.8%	53.2%
LMArena Hard Prompts	1326	1417
DTBench	61.3%	82.7%
LMCA	10.3%	24.3%
SimpleBench	—	40%
Epoch Capabilities Index	—	139.92
ForecastBench	—	58

Math DeepSeek-V3.1 leads

Command A: 36.2 (#171), DeepSeek-V3.1: 38.9 (#122)

Math benchmarks
Benchmark	Command A	DeepSeek-V3.1
LMArena Math	1300	1420

Knowledge DeepSeek-V3.1 leads

Command A: 37.1 (#159), DeepSeek-V3.1: 43.7 (#90)

Knowledge benchmarks
Benchmark	Command A	DeepSeek-V3.1
Vectara Hallucination Rate	9.3%	5.5%
LMArena Expert	1295	1405

Multilingual DeepSeek-V3.1 leads

Command A: 45.3 (#170), DeepSeek-V3.1: 51.6 (#106)

Multilingual benchmarks
Benchmark	Command A	DeepSeek-V3.1
LMArena Non-English	1313	1400
LMArena Chinese	1327	1469
LMArena French	1351	1447
LMArena German	1341	1411
LMArena Japanese	1285	1378
LMArena Korean	1285	1337
LMArena Russian	1314	1405
LMArena Spanish	1347	1431

Instruction Following DeepSeek-V3.1 leads

Command A: 69.1 (#177), DeepSeek-V3.1: 73.9 (#110)

Instruction Following benchmarks
Benchmark	Command A	DeepSeek-V3.1
LMArena Instruction Following	1309	1400

Long Context Command A leads

Command A: 40.6 (#151), DeepSeek-V3.1: 36.3 (#232)

Long Context benchmarks
Benchmark	Command A	DeepSeek-V3.1
LMArena Longer Query	1334	1422
Fiction.LiveBench	—	52.8%

Writing & Preference DeepSeek-V3.1 leads

Command A: 47.6 (#208), DeepSeek-V3.1: 60.3 (#98)

Writing & Preference benchmarks
Benchmark	Command A	DeepSeek-V3.1
LMArena Text	1331	1420
LMArena Creative Writing	1319	1401
EQ-Bench Creative Writing	1145	1436
LMArena Multi-Turn	1339	1408

Frequently asked questions

Is Command A better than DeepSeek-V3.1?

DeepSeek-V3.1 is the stronger model overall, scoring 42.8 to 36.5 on the Noometry Index.

Which is cheaper, Command A or DeepSeek-V3.1?

DeepSeek-V3.1 is cheaper. It lists at $0.25 per million input tokens and $0.95 per million output tokens; Command A lists at $2.50 and $10.

Is Command A or DeepSeek-V3.1 better for coding?

DeepSeek-V3.1 scores higher on coding benchmarks: 40.3 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-V3.1 share?

22 benchmarks have published results for both models. Command A has 24 scored results on Noometry and DeepSeek-V3.1 has 27.