Model comparison

Mistral Large 3 vs Mistral Large 4

Mistral Large 4 is the stronger model overall, scoring 43.1 to 39.1 on the Noometry Index. Mistral Large 3 costs 2.8× less per token, which makes it the better buy when Mistral Large 4's lead doesn't matter for your workload.

Last verified October 10, 2026. 14 shared benchmarks.

Mistral Large 3

Mistral AI

39.1

Rank #176 Confirmed

Mistral Large 4

Mistral AI

43.1

Rank #99 Confirmed

Summary

They share 14 benchmarks with published results for both. Mistral Large 3 scores higher in 0 categories and Mistral Large 4 in 8 categories; 4 gaps are clear of the uncertainty.
The widest gap is in coding, where Mistral Large 4 leads 48.6 to 34.4.
The biggest single-benchmark swing is NYT Connections (extended): 7.5% for Mistral Large 3 and 27.4% for Mistral Large 4.
Mistral Large 3 is cheaper at $0.25 / $0.75 per million input/output tokens, against $0.68 / $2.09 for Mistral Large 4.
Mistral Large 4 accepts more context: 1.05M tokens versus 262K.
Mistral Large 3 has downloadable open weights; the other is API-only.

Side by side

Mistral Large 3 and Mistral Large 4 specifications
	Mistral Large 3	Mistral Large 4
Provider	Mistral AI	Mistral AI
Noometry Index	39.1	43.1
Released	2025-12-02	2026-10-06
Weights	Open	Proprietary
Context window	262K	1.05M
Max output	8K	262K
Input $ / M tokens	$0.25	$0.68
Output $ / M tokens	$0.75	$2.09
Results tracked	24	15

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

Category by category

Coding Mistral Large 4 leads

Mistral Large 3: 34.4 (#237), Mistral Large 4: 48.6 (#57)

Coding benchmarks
Benchmark	Mistral Large 3	Mistral Large 4
LMArena WebDev	1230	1541
LMArena Coding	1448	1475

Reasoning Mistral Large 4 leads

Mistral Large 3: 15.2 (#319), Mistral Large 4: 22.5 (#192)

Reasoning benchmarks
Benchmark	Mistral Large 3	Mistral Large 4
NYT Connections (extended)	7.5%	27.4%
LMArena Hard Prompts	1429	1444
Kagi LLM Benchmark	50.9%	—
Thematic Generalization	23%	—

Math Mistral Large 4 leads

Mistral Large 3: 38.7 (#129), Mistral Large 4: 40.4 (#91)

Math benchmarks
Benchmark	Mistral Large 3	Mistral Large 4
LMArena Math	1414	1488

Knowledge Too close to call

Mistral Large 3: 36.0 (#177), Mistral Large 4: 36.6 (#166)

Knowledge benchmarks
Benchmark	Mistral Large 3	Mistral Large 4
LMArena Expert	1421	1447
SimpleQA Verified	—	20%
Vectara Hallucination Rate	14.5%	—

Multimodal Not comparable

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

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

Multilingual Too close to call

Mistral Large 3: 52.5 (#84), Mistral Large 4: 52.6 (#82)

Multilingual benchmarks
Benchmark	Mistral Large 3	Mistral Large 4
LMArena Non-English	1413	1415
LMArena Chinese	1447	1491
LMArena Russian	1411	1414
LMArena French	1455	—
LMArena German	1437	—
LMArena Japanese	1394	—
LMArena Korean	1384	—
LMArena Spanish	1440	—

Instruction Following Mistral Large 4 leads

Mistral Large 3: 74.0 (#108), Mistral Large 4: 75.0 (#76)

Instruction Following benchmarks
Benchmark	Mistral Large 3	Mistral Large 4
LMArena Instruction Following	1403	1424

Long Context Too close to call

Mistral Large 3: 43.1 (#105), Mistral Large 4: 43.6 (#89)

Long Context benchmarks
Benchmark	Mistral Large 3	Mistral Large 4
LMArena Longer Query	1413	1429

Writing & Preference Too close to call

Mistral Large 3: 60.0 (#101), Mistral Large 4: 60.4 (#97)

Writing & Preference benchmarks
Benchmark	Mistral Large 3	Mistral Large 4
LMArena Text	1428	1427
LMArena Creative Writing	1386	1361
LMArena Multi-Turn	1429	1424
EQ-Bench Creative Writing	1412	—

Frequently asked questions

Is Mistral Large 3 better than Mistral Large 4?

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

Mistral Large 3 is cheaper. It lists at $0.25 per million input tokens and $0.75 per million output tokens; Mistral Large 4 lists at $0.68 and $2.09.

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

Mistral Large 4 scores higher on coding benchmarks: 48.6 versus 34.4 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 3 and Mistral Large 4 share?

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