Model comparison

Mistral Large 4 vs Mistral Medium 3.5

Mistral Large 4 is the stronger model overall, scoring 43.1 to 40.2 on the Noometry Index.

Last verified October 10, 2026. 14 shared benchmarks.

Mistral Large 4

Mistral AI

43.1

Rank #99 Confirmed

Mistral Medium 3.5

Mistral AI

40.2

Rank #152 Confirmed

Summary

They share 14 benchmarks with published results for both. Mistral Large 4 scores higher in 7 categories and Mistral Medium 3.5 in 1 category; 5 gaps are clear of the uncertainty.
The widest gap is in coding, where Mistral Large 4 leads 48.6 to 36.0.
The biggest single-benchmark swing is NYT Connections (extended): 27.4% for Mistral Large 4 and 12.9% for Mistral Medium 3.5.
Mistral Large 4 is cheaper at $0.68 / $2.09 per million input/output tokens, against $1.50 / $7.50 for Mistral Medium 3.5.
Mistral Large 4 accepts more context: 1.05M tokens versus 262K.
Mistral Medium 3.5 has downloadable open weights; the other is API-only.

Side by side

Mistral Large 4 and Mistral Medium 3.5 specifications
	Mistral Large 4	Mistral Medium 3.5
Provider	Mistral AI	Mistral AI
Noometry Index	43.1	40.2
Released	2026-10-06	—
Weights	Proprietary	Open
Context window	1.05M	262K
Max output	262K	210K
Input $ / M tokens	$0.68	$1.50
Output $ / M tokens	$2.09	$7.50
Results tracked	15	22

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

Category by category

Coding Mistral Large 4 leads

Mistral Large 4: 48.6 (#57), Mistral Medium 3.5: 36.0 (#213)

Coding benchmarks
Benchmark	Mistral Large 4	Mistral Medium 3.5
LMArena WebDev	1541	1264
LMArena Coding	1475	1461

Reasoning Mistral Large 4 leads

Mistral Large 4: 22.5 (#192), Mistral Medium 3.5: 17.3 (#295)

Reasoning benchmarks
Benchmark	Mistral Large 4	Mistral Medium 3.5
NYT Connections (extended)	27.4%	12.9%
LMArena Hard Prompts	1444	1436
Kagi LLM Benchmark	—	41.4%
Epoch Capabilities Index	—	141.35

Math Mistral Large 4 leads

Mistral Large 4: 40.4 (#91), Mistral Medium 3.5: 39.1 (#113)

Math benchmarks
Benchmark	Mistral Large 4	Mistral Medium 3.5
LMArena Math	1488	1431

Knowledge Mistral Medium 3.5 leads

Mistral Large 4: 36.6 (#166), Mistral Medium 3.5: 40.0 (#126)

Knowledge benchmarks
Benchmark	Mistral Large 4	Mistral Medium 3.5
LMArena Expert	1447	1432
SimpleQA Verified	20%	—

Multimodal Not comparable

Mistral Large 4: —, Mistral Medium 3.5: 38.3 (#65)

Multimodal benchmarks
Benchmark	Mistral Large 4	Mistral Medium 3.5
LMArena Vision	—	1223

Multilingual Too close to call

Mistral Large 4: 52.6 (#82), Mistral Medium 3.5: 51.9 (#100)

Multilingual benchmarks
Benchmark	Mistral Large 4	Mistral Medium 3.5
LMArena Non-English	1415	1404
LMArena Chinese	1491	1442
LMArena Russian	1414	1395
LMArena French	—	1448
LMArena German	—	1451
LMArena Korean	—	1385
LMArena Spanish	—	1409

Instruction Following Too close to call

Mistral Large 4: 75.0 (#76), Mistral Medium 3.5: 74.6 (#90)

Instruction Following benchmarks
Benchmark	Mistral Large 4	Mistral Medium 3.5
LMArena Instruction Following	1424	1415

Long Context Too close to call

Mistral Large 4: 43.6 (#89), Mistral Medium 3.5: 43.2 (#103)

Long Context benchmarks
Benchmark	Mistral Large 4	Mistral Medium 3.5
LMArena Longer Query	1429	1415

Writing & Preference Mistral Large 4 leads

Mistral Large 4: 60.4 (#97), Mistral Medium 3.5: 58.5 (#117)

Writing & Preference benchmarks
Benchmark	Mistral Large 4	Mistral Medium 3.5
LMArena Text	1427	1421
LMArena Creative Writing	1361	1374
LMArena Multi-Turn	1424	1423
EQ-Bench 4	—	993

Frequently asked questions

Is Mistral Large 4 better than Mistral Medium 3.5?

Mistral Large 4 is the stronger model overall, scoring 43.1 to 40.2 on the Noometry Index.

Which is cheaper, Mistral Large 4 or Mistral Medium 3.5?

Mistral Large 4 is cheaper. It lists at $0.68 per million input tokens and $2.09 per million output tokens; Mistral Medium 3.5 lists at $1.50 and $7.50.

Is Mistral Large 4 or Mistral Medium 3.5 better for coding?

Mistral Large 4 scores higher on coding benchmarks: 48.6 versus 36.0 in the Noometry coding category.

Which has the bigger context window?

Mistral Large 4 does, with 1.05M tokens against 262K.

How many benchmarks do Mistral Large 4 and Mistral Medium 3.5 share?

14 benchmarks have published results for both models. Mistral Large 4 has 15 scored results on Noometry and Mistral Medium 3.5 has 22.