Model comparison

Gemma 3 4B vs Mistral Large 3

Mistral Large 3 is the stronger model overall, scoring 39.1 to 28.1 on the Noometry Index. Gemma 3 4B costs 7.5× less per token, which makes it the better buy when Mistral Large 3's lead doesn't matter for your workload.

Last verified October 10, 2026. 15 shared benchmarks.

Gemma 3 4B

Google

28.1

Rank #326 Confirmed

Mistral Large 3

Mistral AI

39.1

Rank #176 Confirmed

Summary

They share 15 benchmarks with published results for both. Gemma 3 4B scores higher in 1 category and Mistral Large 3 in 7 categories; 8 gaps are clear of the uncertainty.
The widest gap is in knowledge, where Mistral Large 3 leads 36.0 to 11.8.
The biggest single-benchmark swing is Kagi LLM Benchmark: 25.2% for Gemma 3 4B and 50.9% for Mistral Large 3.
Gemma 3 4B is cheaper at $0.04 / $0.08 per million input/output tokens, against $0.25 / $0.75 for Mistral Large 3.
Mistral Large 3 accepts more context: 262K tokens versus 131K.

Side by side

Gemma 3 4B and Mistral Large 3 specifications
	Gemma 3 4B	Mistral Large 3
Provider	Google	Mistral AI
Noometry Index	28.1	39.1
Released	2025-03-12	2025-12-02
Weights	Open	Open
Context window	131K	262K
Max output	4K	8K
Input $ / M tokens	$0.04	$0.25
Output $ / M tokens	$0.08	$0.75
Results tracked	22	24

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

Category by category

Coding Gemma 3 4B leads

Gemma 3 4B: 35.9 (#215), Mistral Large 3: 34.4 (#237)

Coding benchmarks
Benchmark	Gemma 3 4B	Mistral Large 3
LMArena Coding	1230	1448
LMArena WebDev	—	1230

Agentic & Tool Use Not comparable

Gemma 3 4B: 20.9 (#142), Mistral Large 3: —

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

Reasoning Mistral Large 3 leads

Gemma 3 4B: 13.2 (#335), Mistral Large 3: 15.2 (#319)

Reasoning benchmarks
Benchmark	Gemma 3 4B	Mistral Large 3
Kagi LLM Benchmark	25.2%	50.9%
LMArena Hard Prompts	1253	1429
NYT Connections (extended)	—	7.5%
Chess Puzzles	0%	—
Thematic Generalization	—	23%
DTBench	50.9%	—
LMCA	2.8%	—
Epoch Capabilities Index	116.02	—

Math Mistral Large 3 leads

Gemma 3 4B: 16.8 (#292), Mistral Large 3: 38.7 (#129)

Math benchmarks
Benchmark	Gemma 3 4B	Mistral Large 3
LMArena Math	1239	1414
OTIS Mock AIME 2024-2025	7.5%	—

Knowledge Mistral Large 3 leads

Gemma 3 4B: 11.8 (#299), Mistral Large 3: 36.0 (#177)

Knowledge benchmarks
Benchmark	Gemma 3 4B	Mistral Large 3
Vectara Hallucination Rate	6.4%	14.5%
LMArena Expert	1223	1421
GPQA Diamond	23.2%	—

Multimodal Not comparable

Gemma 3 4B: —, Mistral Large 3: 38.2 (#66)

Multimodal benchmarks
Benchmark	Gemma 3 4B	Mistral Large 3
LMArena Vision	—	1221

Multilingual Mistral Large 3 leads

Gemma 3 4B: 42.5 (#194), Mistral Large 3: 52.5 (#84)

Multilingual benchmarks
Benchmark	Gemma 3 4B	Mistral Large 3
LMArena Non-English	1273	1413
LMArena German	1281	1437
LMArena Russian	1294	1411
LMArena Chinese	—	1447
LMArena French	—	1455
LMArena Japanese	—	1394
LMArena Korean	—	1384
LMArena Spanish	—	1440

Instruction Following Mistral Large 3 leads

Gemma 3 4B: 65.2 (#225), Mistral Large 3: 74.0 (#108)

Instruction Following benchmarks
Benchmark	Gemma 3 4B	Mistral Large 3
LMArena Instruction Following	1239	1403

Long Context Mistral Large 3 leads

Gemma 3 4B: 38.7 (#194), Mistral Large 3: 43.1 (#105)

Long Context benchmarks
Benchmark	Gemma 3 4B	Mistral Large 3
LMArena Longer Query	1273	1413

Writing & Preference Mistral Large 3 leads

Gemma 3 4B: 42.0 (#239), Mistral Large 3: 60.0 (#101)

Writing & Preference benchmarks
Benchmark	Gemma 3 4B	Mistral Large 3
LMArena Text	1291	1428
LMArena Creative Writing	1271	1386
EQ-Bench Creative Writing	1068	1412
LMArena Multi-Turn	1255	1429

Frequently asked questions

Is Gemma 3 4B better than Mistral Large 3?

Which is cheaper, Gemma 3 4B or Mistral Large 3?

Gemma 3 4B is cheaper. It lists at $0.04 per million input tokens and $0.08 per million output tokens; Mistral Large 3 lists at $0.25 and $0.75.

Is Gemma 3 4B or Mistral Large 3 better for coding?

Gemma 3 4B scores higher on coding benchmarks: 35.9 versus 34.4 in the Noometry coding category.

Which has the bigger context window?

Mistral Large 3 does, with 262K tokens against 131K.

How many benchmarks do Gemma 3 4B and Mistral Large 3 share?

15 benchmarks have published results for both models. Gemma 3 4B has 22 scored results on Noometry and Mistral Large 3 has 24.