Model comparison

Codestral vs Gemma 3 4B

Codestral is the stronger model overall, scoring 30.6 to 28.1 on the Noometry Index. Gemma 3 4B costs 9.0× less per token, which makes it the better buy when Codestral's lead doesn't matter for your workload.

Last verified October 10, 2026. 1 shared benchmarks.

Codestral

Mistral AI

30.6

Rank #290 Reported

Gemma 3 4B

Google

28.1

Rank #326 Confirmed

Summary

They share 1 benchmark with published results for both. Codestral scores higher in 1 category and Gemma 3 4B in 1 category; 2 gaps are clear of the uncertainty.
The widest gap is in coding, where Gemma 3 4B leads 35.9 to 27.3.
The biggest single-benchmark swing is Kagi LLM Benchmark: 32.5% for Codestral and 25.2% for Gemma 3 4B.
Gemma 3 4B is cheaper at $0.04 / $0.08 per million input/output tokens, against $0.30 / $0.90 for Codestral.
Codestral accepts more context: 256K tokens versus 131K.
Gemma 3 4B has downloadable open weights; the other is API-only.

Side by side

Codestral and Gemma 3 4B specifications
	Codestral	Gemma 3 4B
Provider	Mistral AI	Google
Noometry Index	30.6	28.1
Released	2024-05-29	2025-03-12
Weights	Proprietary	Open
Context window	256K	131K
Max output	8K	4K
Input $ / M tokens	$0.30	$0.04
Output $ / M tokens	$0.90	$0.08
Results tracked	7	22

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

Category by category

Coding Gemma 3 4B leads

Codestral: 27.3 (#321), Gemma 3 4B: 35.9 (#215)

Coding benchmarks
Benchmark	Codestral	Gemma 3 4B
Aider Polyglot	11.1%	—
BigCodeBench Instruct	41.8%	—
LMArena Coding	—	1230
BigCodeBench Complete	52.5%	—
ALE-Bench	137.78	—
HumanEval+	73.8%	—
MBPP+	61.9%	—

Agentic & Tool Use Not comparable

Codestral: —, Gemma 3 4B: 20.9 (#142)

Agentic & Tool Use benchmarks
Benchmark	Codestral	Gemma 3 4B
Berkeley Function Calling Leaderboard	—	19.6%

Reasoning Codestral leads

Codestral: 19.8 (#251), Gemma 3 4B: 13.2 (#335)

Reasoning benchmarks
Benchmark	Codestral	Gemma 3 4B
Kagi LLM Benchmark	32.5%	25.2%
Chess Puzzles	—	0%
LMArena Hard Prompts	—	1253
DTBench	—	50.9%
LMCA	—	2.8%
Epoch Capabilities Index	—	116.02

Math Not comparable

Codestral: —, Gemma 3 4B: 16.8 (#292)

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

Knowledge Not comparable

Codestral: —, Gemma 3 4B: 11.8 (#299)

Knowledge benchmarks
Benchmark	Codestral	Gemma 3 4B
GPQA Diamond	—	23.2%
Vectara Hallucination Rate	—	6.4%
LMArena Expert	—	1223

Multilingual Not comparable

Codestral: —, Gemma 3 4B: 42.5 (#194)

Multilingual benchmarks
Benchmark	Codestral	Gemma 3 4B
LMArena Non-English	—	1273
LMArena German	—	1281
LMArena Russian	—	1294

Instruction Following Not comparable

Codestral: —, Gemma 3 4B: 65.2 (#225)

Instruction Following benchmarks
Benchmark	Codestral	Gemma 3 4B
LMArena Instruction Following	—	1239

Long Context Not comparable

Codestral: —, Gemma 3 4B: 38.7 (#194)

Long Context benchmarks
Benchmark	Codestral	Gemma 3 4B
LMArena Longer Query	—	1273

Writing & Preference Not comparable

Codestral: —, Gemma 3 4B: 42.0 (#239)

Writing & Preference benchmarks
Benchmark	Codestral	Gemma 3 4B
LMArena Text	—	1291
LMArena Creative Writing	—	1271
EQ-Bench Creative Writing	—	1068
LMArena Multi-Turn	—	1255

Frequently asked questions

Is Codestral better than Gemma 3 4B?

Which is cheaper, Codestral 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; Codestral lists at $0.30 and $0.90.

Is Codestral or Gemma 3 4B better for coding?

Gemma 3 4B scores higher on coding benchmarks: 35.9 versus 27.3 in the Noometry coding category.

Which has the bigger context window?

Codestral does, with 256K tokens against 131K.

How many benchmarks do Codestral and Gemma 3 4B share?

1 benchmark has published results for both models. Codestral has 7 scored results on Noometry and Gemma 3 4B has 22.