Model comparison

Gemma 3 27B vs Mistral Medium 3.5

Mistral Medium 3.5 is the stronger model overall, scoring 40.2 to 30.8 on the Noometry Index. Gemma 3 27B costs 30× 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 10, 2026. 19 shared benchmarks.

Gemma 3 27B

Google

30.8

Rank #284 Confirmed

Mistral Medium 3.5

Mistral AI

40.2

Rank #152 Confirmed

Summary

They share 19 benchmarks with published results for both. Gemma 3 27B scores higher in 0 categories and Mistral Medium 3.5 in 9 categories; 8 gaps are clear of the uncertainty.
The widest gap is in long context, where Mistral Medium 3.5 leads 43.2 to 27.6.
Gemma 3 27B is cheaper at $0.08 / $0.16 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 27B and Mistral Medium 3.5 specifications
	Gemma 3 27B	Mistral Medium 3.5
Provider	Google	Mistral AI
Noometry Index	30.8	40.2
Released	2025-03-11	—
Weights	Open	Open
Context window	131K	262K
Max output	8K	210K
Input $ / M tokens	$0.08	$1.50
Output $ / M tokens	$0.16	$7.50
Results tracked	43	22

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

Category by category

Coding Mistral Medium 3.5 leads

Gemma 3 27B: 22.5 (#334), Mistral Medium 3.5: 36.0 (#213)

Coding benchmarks
Benchmark	Gemma 3 27B	Mistral Medium 3.5
LMArena Coding	1322	1461
Aider Polyglot	4.9%	—
LMArena WebDev	—	1264
SciCode	21.2%	—
LiveBench Coding	39.9%	—

Agentic & Tool Use Not comparable

Gemma 3 27B: 25.1 (#110), Mistral Medium 3.5: —

Agentic & Tool Use benchmarks
Benchmark	Gemma 3 27B	Mistral Medium 3.5
Berkeley Function Calling Leaderboard	29.5%	—

Reasoning Too close to call

Gemma 3 27B: 16.7 (#301), Mistral Medium 3.5: 17.3 (#295)

Reasoning benchmarks
Benchmark	Gemma 3 27B	Mistral Medium 3.5
Kagi LLM Benchmark	40.4%	41.4%
LMArena Hard Prompts	1340	1436
Epoch Capabilities Index	130.04	141.35
NYT Connections (extended)	—	12.9%
CritPt	0%	—
Chess Puzzles	0%	—
LiveBench Reasoning	43.8%	—
DTBench	52.5%	—
LiveBench Data Analysis	51.5%	—
LMCA	12.3%	—
LiveBench	50%	—

Math Mistral Medium 3.5 leads

Gemma 3 27B: 25.9 (#265), Mistral Medium 3.5: 39.1 (#113)

Math benchmarks
Benchmark	Gemma 3 27B	Mistral Medium 3.5
LMArena Math	1312	1431
OTIS Mock AIME 2024-2025	22.5%	—
LiveBench Math	55.4%	—
MATH Level 5	74%	—

Knowledge Mistral Medium 3.5 leads

Gemma 3 27B: 25.5 (#261), Mistral Medium 3.5: 40.0 (#126)

Knowledge benchmarks
Benchmark	Gemma 3 27B	Mistral Medium 3.5
LMArena Expert	1304	1432
GPQA Diamond	47.7%	—
Confabulations	40.3%	—
Vectara Hallucination Rate	7.4%	—

Multimodal Mistral Medium 3.5 leads

Gemma 3 27B: 32.6 (#100), Mistral Medium 3.5: 38.3 (#65)

Multimodal benchmarks
Benchmark	Gemma 3 27B	Mistral Medium 3.5
LMArena Vision	1164	1223
GeoBench	52%	—

Multilingual Mistral Medium 3.5 leads

Gemma 3 27B: 46.9 (#155), Mistral Medium 3.5: 51.9 (#100)

Multilingual benchmarks
Benchmark	Gemma 3 27B	Mistral Medium 3.5
LMArena Non-English	1334	1404
LMArena Chinese	1346	1442
LMArena French	1368	1448
LMArena German	1362	1451
LMArena Korean	1308	1385
LMArena Russian	1349	1395
LMArena Spanish	1349	1409
LMArena Japanese	1287	—

Instruction Following Mistral Medium 3.5 leads

Gemma 3 27B: 70.6 (#160), Mistral Medium 3.5: 74.6 (#90)

Instruction Following benchmarks
Benchmark	Gemma 3 27B	Mistral Medium 3.5
LMArena Instruction Following	1321	1415
LiveBench Instruction Following	74.9%	—

Long Context Mistral Medium 3.5 leads

Gemma 3 27B: 27.6 (#293), Mistral Medium 3.5: 43.2 (#103)

Long Context benchmarks
Benchmark	Gemma 3 27B	Mistral Medium 3.5
LMArena Longer Query	1333	1415
Fiction.LiveBench	33.3%	—

Writing & Preference Mistral Medium 3.5 leads

Gemma 3 27B: 52.5 (#168), Mistral Medium 3.5: 58.5 (#117)

Writing & Preference benchmarks
Benchmark	Gemma 3 27B	Mistral Medium 3.5
LMArena Text	1358	1421
LMArena Creative Writing	1346	1374
LMArena Multi-Turn	1345	1423
Short-Story Creative Writing	79.9%	—
EQ-Bench Creative Writing	1266	—
EQ-Bench 4	—	993
LiveBench Language	34.6%	—

Frequently asked questions

Is Gemma 3 27B better than Mistral Medium 3.5?

Which is cheaper, Gemma 3 27B or Mistral Medium 3.5?

Gemma 3 27B is cheaper. It lists at $0.08 per million input tokens and $0.16 per million output tokens; Mistral Medium 3.5 lists at $1.50 and $7.50.

Is Gemma 3 27B or Mistral Medium 3.5 better for coding?

Mistral Medium 3.5 scores higher on coding benchmarks: 36.0 versus 22.5 in the Noometry coding category.

Which has the bigger context window?

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

How many benchmarks do Gemma 3 27B and Mistral Medium 3.5 share?

19 benchmarks have published results for both models. Gemma 3 27B has 43 scored results on Noometry and Mistral Medium 3.5 has 22.