Model comparison

Command R vs DeepSeek-V3.2-Speciale

DeepSeek-V3.2-Speciale is the stronger model overall, scoring 39.7 to 31.4 on the Noometry Index. Command R costs 3.3× less per token, which makes it the better buy when DeepSeek-V3.2-Speciale's lead doesn't matter for your workload.

Last verified October 10, 2026. 0 shared benchmarks.

Command R

Cohere

31.4

Rank #272 Confirmed

DeepSeek-V3.2-Speciale

DeepSeek

39.7

Rank #162 Reported

Summary

The widest gap is in reasoning, where DeepSeek-V3.2-Speciale leads 32.9 to 13.8.
Command R is cheaper at $0.15 / $0.60 per million input/output tokens, against $0.58 / $1.68 for DeepSeek-V3.2-Speciale.

Side by side

Command R and DeepSeek-V3.2-Speciale specifications
	Command R	DeepSeek-V3.2-Speciale
Provider	Cohere	DeepSeek
Noometry Index	31.4	39.7
Released	2024-08-30	2025-12-01
Weights	Open	Open
Context window	128K	128K
Max output	4K	128K
Input $ / M tokens	$0.15	$0.58
Output $ / M tokens	$0.60	$1.68
Results tracked	29	3

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

Category by category

Coding DeepSeek-V3.2-Speciale leads

Command R: 29.3 (#306), DeepSeek-V3.2-Speciale: 40.4 (#140)

Coding benchmarks
Benchmark	Command R	DeepSeek-V3.2-Speciale
WeirdML	—	46.7%
BigCodeBench Instruct	37.1%	—
LiveBench Coding	17.9%	—
LMArena Coding	1169	—
BigCodeBench Complete	45.2%	—

Reasoning DeepSeek-V3.2-Speciale leads

Command R: 13.8 (#331), DeepSeek-V3.2-Speciale: 32.9 (#73)

Reasoning benchmarks
Benchmark	Command R	DeepSeek-V3.2-Speciale
SimpleBench	—	52.6%
LiveBench Reasoning	21.9%	—
LMArena Hard Prompts	1164	—
DTBench	46.4%	—
LiveBench Data Analysis	33.3%	—
LMCA	9.2%	—
LiveBench	27.5%	—

Math Not comparable

Command R: 28.0 (#246), DeepSeek-V3.2-Speciale: —

Math benchmarks
Benchmark	Command R	DeepSeek-V3.2-Speciale
LiveBench Math	19.4%	—
LMArena Math	1155	—

Knowledge Not comparable

Command R: 31.0 (#221), DeepSeek-V3.2-Speciale: —

Knowledge benchmarks
Benchmark	Command R	DeepSeek-V3.2-Speciale
LMArena Expert	1138	—
MMLU	65.2%	—

Multilingual Not comparable

Command R: 35.7 (#245), DeepSeek-V3.2-Speciale: —

Multilingual benchmarks
Benchmark	Command R	DeepSeek-V3.2-Speciale
LMArena Non-English	1174	—
LMArena Chinese	1182	—
LMArena French	1162	—
LMArena German	1176	—
LMArena Japanese	1143	—
LMArena Korean	1163	—
LMArena Russian	1174	—
LMArena Spanish	1151	—

Instruction Following Not comparable

Command R: 58.1 (#261), DeepSeek-V3.2-Speciale: —

Instruction Following benchmarks
Benchmark	Command R	DeepSeek-V3.2-Speciale
LiveBench Instruction Following	55.6%	—
LMArena Instruction Following	1167	—

Long Context Not comparable

Command R: 36.3 (#231), DeepSeek-V3.2-Speciale: —

Long Context benchmarks
Benchmark	Command R	DeepSeek-V3.2-Speciale
LMArena Longer Query	1198	—

Writing & Preference DeepSeek-V3.2-Speciale leads

Command R: 38.2 (#254), DeepSeek-V3.2-Speciale: 46.0 (#222)

Writing & Preference benchmarks
Benchmark	Command R	DeepSeek-V3.2-Speciale
LMArena Text	1187	—
LMArena Creative Writing	1170	—
EQ-Bench Creative Writing	—	1276
LMArena Multi-Turn	1163	—
LiveBench Language	16.7%	—

Frequently asked questions

Is Command R better than DeepSeek-V3.2-Speciale?

Which is cheaper, Command R or DeepSeek-V3.2-Speciale?

Command R is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; DeepSeek-V3.2-Speciale lists at $0.58 and $1.68.

Is Command R or DeepSeek-V3.2-Speciale better for coding?

DeepSeek-V3.2-Speciale scores higher on coding benchmarks: 40.4 versus 29.3 in the Noometry coding category.

Which has the bigger context window?

Both accept 128K tokens.

How many benchmarks do Command R and DeepSeek-V3.2-Speciale share?

0 benchmarks have published results for both models. Command R has 29 scored results on Noometry and DeepSeek-V3.2-Speciale has 3.