Model comparison

Gemma 3 4B vs Mistral Medium 3.5

Mistral Medium 3.5 is the stronger model overall, scoring 40.2 to 28.1 on the Noometry Index. Gemma 3 4B costs 60× less per token, which makes it the better buy when Mistral Medium 3.5's lead doesn't matter for your workload.

Last verified October 11, 2026. 14 shared benchmarks.

Gemma 3 4B

Google

28.1

Rank #326 Confirmed

Mistral Medium 3.5

Mistral AI

40.2

Rank #152 Confirmed

Summary

They share 14 benchmarks with published results for both. Gemma 3 4B scores higher in 0 categories and Mistral Medium 3.5 in 8 categories; 7 gaps are clear of the uncertainty.
The widest gap is in knowledge, where Mistral Medium 3.5 leads 40.0 to 11.8.
The biggest single-benchmark swing is Kagi LLM Benchmark: 25.2% for Gemma 3 4B and 41.4% for Mistral Medium 3.5.
Gemma 3 4B is cheaper at $0.04 / $0.08 per million input/output tokens, against $1.50 / $7.50 for Mistral Medium 3.5.
Mistral Medium 3.5 accepts more context: 262K tokens versus 131K.

Side by side

Gemma 3 4B and Mistral Medium 3.5 specifications
	Gemma 3 4B	Mistral Medium 3.5
Provider	Google	Mistral AI
Noometry Index	28.1	40.2
Released	2025-03-12	—
Weights	Open	Open
Context window	131K	262K
Max output	4K	210K
Input $ / M tokens	$0.04	$1.50
Output $ / M tokens	$0.08	$7.50
Results tracked	22	22

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

Category by category

Coding Too close to call

Gemma 3 4B: 35.9 (#215), Mistral Medium 3.5: 36.0 (#213)

Coding benchmarks
Benchmark	Gemma 3 4B	Mistral Medium 3.5
LMArena Coding	1230	1461
LMArena WebDev	—	1264

Agentic & Tool Use Not comparable

Gemma 3 4B: 20.9 (#142), Mistral Medium 3.5: —

Agentic & Tool Use benchmarks
Benchmark	Gemma 3 4B	Mistral Medium 3.5
Berkeley Function Calling Leaderboard	19.6%	—

Reasoning Mistral Medium 3.5 leads

Gemma 3 4B: 13.2 (#335), Mistral Medium 3.5: 17.3 (#295)

Reasoning benchmarks
Benchmark	Gemma 3 4B	Mistral Medium 3.5
Kagi LLM Benchmark	25.2%	41.4%
LMArena Hard Prompts	1253	1436
Epoch Capabilities Index	116.02	141.35
NYT Connections (extended)	—	12.9%
Chess Puzzles	0%	—
DTBench	50.9%	—
LMCA	2.8%	—

Math Mistral Medium 3.5 leads

Gemma 3 4B: 16.8 (#292), Mistral Medium 3.5: 39.1 (#113)

Math benchmarks
Benchmark	Gemma 3 4B	Mistral Medium 3.5
LMArena Math	1239	1431
OTIS Mock AIME 2024-2025	7.5%	—

Knowledge Mistral Medium 3.5 leads

Gemma 3 4B: 11.8 (#299), Mistral Medium 3.5: 40.0 (#126)

Knowledge benchmarks
Benchmark	Gemma 3 4B	Mistral Medium 3.5
LMArena Expert	1223	1432
GPQA Diamond	23.2%	—
Vectara Hallucination Rate	6.4%	—

Multimodal Not comparable

Gemma 3 4B: —, Mistral Medium 3.5: 38.3 (#65)

Multimodal benchmarks
Benchmark	Gemma 3 4B	Mistral Medium 3.5
LMArena Vision	—	1223

Multilingual Mistral Medium 3.5 leads

Gemma 3 4B: 42.5 (#194), Mistral Medium 3.5: 51.9 (#100)

Multilingual benchmarks
Benchmark	Gemma 3 4B	Mistral Medium 3.5
LMArena Non-English	1273	1404
LMArena German	1281	1451
LMArena Russian	1294	1395
LMArena Chinese	—	1442
LMArena French	—	1448
LMArena Korean	—	1385
LMArena Spanish	—	1409

Instruction Following Mistral Medium 3.5 leads

Gemma 3 4B: 65.2 (#225), Mistral Medium 3.5: 74.6 (#90)

Instruction Following benchmarks
Benchmark	Gemma 3 4B	Mistral Medium 3.5
LMArena Instruction Following	1239	1415

Long Context Mistral Medium 3.5 leads

Gemma 3 4B: 38.7 (#194), Mistral Medium 3.5: 43.2 (#103)

Long Context benchmarks
Benchmark	Gemma 3 4B	Mistral Medium 3.5
LMArena Longer Query	1273	1415

Writing & Preference Mistral Medium 3.5 leads

Gemma 3 4B: 42.0 (#239), Mistral Medium 3.5: 58.5 (#117)

Writing & Preference benchmarks
Benchmark	Gemma 3 4B	Mistral Medium 3.5
LMArena Text	1291	1421
LMArena Creative Writing	1271	1374
LMArena Multi-Turn	1255	1423
EQ-Bench Creative Writing	1068	—
EQ-Bench 4	—	993

Frequently asked questions

Is Gemma 3 4B better than Mistral Medium 3.5?

Which is cheaper, Gemma 3 4B or Mistral Medium 3.5?

Gemma 3 4B is cheaper. It lists at $0.04 per million input tokens and $0.08 per million output tokens; Mistral Medium 3.5 lists at $1.50 and $7.50.

Is Gemma 3 4B or Mistral Medium 3.5 better for coding?

They score almost the same on coding (35.9 vs 36.0); test both on your own repository before choosing.

Which has the bigger context window?

Mistral Medium 3.5 does, with 262K tokens against 131K.

How many benchmarks do Gemma 3 4B and Mistral Medium 3.5 share?

14 benchmarks have published results for both models. Gemma 3 4B has 22 scored results on Noometry and Mistral Medium 3.5 has 22.