Model comparison

Command A vs Gemma 3 4B

Command A is the stronger model overall, scoring 36.5 to 28.1 on the Noometry Index. Gemma 3 4B costs 88× less per token, which makes it the better buy when Command A's lead doesn't matter for your workload.

Last verified October 11, 2026. 18 shared benchmarks.

Command A

Cohere

36.5

Rank #215 Confirmed

Gemma 3 4B

Google

28.1

Rank #326 Confirmed

Summary

They share 18 benchmarks with published results for both. Command A scores higher in 8 categories and Gemma 3 4B in 1 category; 9 gaps are clear of the uncertainty.
The widest gap is in knowledge, where Command A leads 37.1 to 11.8.
The biggest single-benchmark swing is Berkeley Function Calling Leaderboard: 57.1% for Command A and 19.6% for Gemma 3 4B.
Gemma 3 4B is cheaper at $0.04 / $0.08 per million input/output tokens, against $2.50 / $10 for Command A.
Command A accepts more context: 256K tokens versus 131K.

Side by side

Command A and Gemma 3 4B specifications
	Command A	Gemma 3 4B
Provider	Cohere	Google
Noometry Index	36.5	28.1
Released	2025-03-13	2025-03-12
Weights	Open	Open
Context window	256K	131K
Max output	8K	4K
Input $ / M tokens	$2.50	$0.04
Output $ / M tokens	$10	$0.08
Results tracked	24	22

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

Category by category

Coding Gemma 3 4B leads

Command A: 27.2 (#322), Gemma 3 4B: 35.9 (#215)

Coding benchmarks
Benchmark	Command A	Gemma 3 4B
LMArena Coding	1330	1230
Aider Polyglot	12%	—

Agentic & Tool Use Command A leads

Command A: 35.9 (#40), Gemma 3 4B: 20.9 (#142)

Agentic & Tool Use benchmarks
Benchmark	Command A	Gemma 3 4B
Berkeley Function Calling Leaderboard	57.1%	19.6%

Reasoning Command A leads

Command A: 18.3 (#283), Gemma 3 4B: 13.2 (#335)

Reasoning benchmarks
Benchmark	Command A	Gemma 3 4B
Kagi LLM Benchmark	28.8%	25.2%
LMArena Hard Prompts	1326	1253
DTBench	61.3%	50.9%
LMCA	10.3%	2.8%
Chess Puzzles	—	0%
Epoch Capabilities Index	—	116.02

Math Command A leads

Command A: 36.2 (#171), Gemma 3 4B: 16.8 (#292)

Math benchmarks
Benchmark	Command A	Gemma 3 4B
LMArena Math	1300	1239
OTIS Mock AIME 2024-2025	—	7.5%

Knowledge Command A leads

Command A: 37.1 (#159), Gemma 3 4B: 11.8 (#299)

Knowledge benchmarks
Benchmark	Command A	Gemma 3 4B
Vectara Hallucination Rate	9.3%	6.4%
LMArena Expert	1295	1223
GPQA Diamond	—	23.2%

Multilingual Command A leads

Command A: 45.3 (#170), Gemma 3 4B: 42.5 (#194)

Multilingual benchmarks
Benchmark	Command A	Gemma 3 4B
LMArena Non-English	1313	1273
LMArena German	1341	1281
LMArena Russian	1314	1294
LMArena Chinese	1327	—
LMArena French	1351	—
LMArena Japanese	1285	—
LMArena Korean	1285	—
LMArena Spanish	1347	—

Instruction Following Command A leads

Command A: 69.1 (#177), Gemma 3 4B: 65.2 (#225)

Instruction Following benchmarks
Benchmark	Command A	Gemma 3 4B
LMArena Instruction Following	1309	1239

Long Context Command A leads

Command A: 40.6 (#151), Gemma 3 4B: 38.7 (#194)

Long Context benchmarks
Benchmark	Command A	Gemma 3 4B
LMArena Longer Query	1334	1273

Writing & Preference Command A leads

Command A: 47.6 (#208), Gemma 3 4B: 42.0 (#239)

Writing & Preference benchmarks
Benchmark	Command A	Gemma 3 4B
LMArena Text	1331	1291
LMArena Creative Writing	1319	1271
EQ-Bench Creative Writing	1145	1068
LMArena Multi-Turn	1339	1255

Frequently asked questions

Is Command A better than Gemma 3 4B?

Which is cheaper, Command A or Gemma 3 4B?

Gemma 3 4B is cheaper. It lists at $0.04 per million input tokens and $0.08 per million output tokens; Command A lists at $2.50 and $10.

Is Command A or Gemma 3 4B better for coding?

Gemma 3 4B scores higher on coding benchmarks: 35.9 versus 27.2 in the Noometry coding category.

Which has the bigger context window?

Command A does, with 256K tokens against 131K.

How many benchmarks do Command A and Gemma 3 4B share?

18 benchmarks have published results for both models. Command A has 24 scored results on Noometry and Gemma 3 4B has 22.