Model comparison

Mistral Large 4 vs Mistral Small 3.2

Mistral Large 4 is the stronger model overall, scoring 43.1 to 31.2 on the Noometry Index. Mistral Small 3.2 costs 7.8× 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. 0 shared benchmarks.

Mistral Large 4

Mistral AI

43.1

Rank #99 Confirmed

Mistral Small 3.2

Mistral AI

31.2

Rank #280 Confirmed

Summary

The widest gap is in writing & preference, where Mistral Large 4 leads 60.4 to 45.0.
Mistral Small 3.2 is cheaper at $0.0938 / $0.25 per million input/output tokens, against $0.68 / $2.09 for Mistral Large 4.
Mistral Large 4 accepts more context: 1.05M tokens versus 256K.
Mistral Small 3.2 has downloadable open weights; the other is API-only.

Side by side

Mistral Large 4 and Mistral Small 3.2 specifications
	Mistral Large 4	Mistral Small 3.2
Provider	Mistral AI	Mistral AI
Noometry Index	43.1	31.2
Released	2026-10-06	2025-06-20
Weights	Proprietary	Open
Context window	1.05M	256K
Max output	262K	16K
Input $ / M tokens	$0.68	$0.0938
Output $ / M tokens	$2.09	$0.25
Results tracked	15	6

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

Category by category

Coding Not comparable

Mistral Large 4: 48.6 (#57), Mistral Small 3.2: —

Coding benchmarks
Benchmark	Mistral Large 4	Mistral Small 3.2
LMArena WebDev	1541	—
LMArena Coding	1475	—

Reasoning Mistral Large 4 leads

Mistral Large 4: 22.5 (#192), Mistral Small 3.2: 18.1 (#287)

Reasoning benchmarks
Benchmark	Mistral Large 4	Mistral Small 3.2
Kagi LLM Benchmark	—	40.4%
NYT Connections (extended)	27.4%	—
Chess Puzzles	—	1%
LMArena Hard Prompts	1444	—
Epoch Capabilities Index	—	131.74

Math Mistral Large 4 leads

Mistral Large 4: 40.4 (#91), Mistral Small 3.2: 26.3 (#260)

Math benchmarks
Benchmark	Mistral Large 4	Mistral Small 3.2
OTIS Mock AIME 2024-2025	—	30.3%
LMArena Math	1488	—

Knowledge Mistral Large 4 leads

Mistral Large 4: 36.6 (#166), Mistral Small 3.2: 26.7 (#256)

Knowledge benchmarks
Benchmark	Mistral Large 4	Mistral Small 3.2
GPQA Diamond	—	49.1%
SimpleQA Verified	20%	—
LMArena Expert	1447	—

Multilingual Not comparable

Mistral Large 4: 52.6 (#82), Mistral Small 3.2: —

Multilingual benchmarks
Benchmark	Mistral Large 4	Mistral Small 3.2
LMArena Non-English	1415	—
LMArena Chinese	1491	—
LMArena Russian	1414	—

Instruction Following Not comparable

Mistral Large 4: 75.0 (#76), Mistral Small 3.2: —

Instruction Following benchmarks
Benchmark	Mistral Large 4	Mistral Small 3.2
LMArena Instruction Following	1424	—

Long Context Not comparable

Mistral Large 4: 43.6 (#89), Mistral Small 3.2: —

Long Context benchmarks
Benchmark	Mistral Large 4	Mistral Small 3.2
LMArena Longer Query	1429	—

Writing & Preference Mistral Large 4 leads

Mistral Large 4: 60.4 (#97), Mistral Small 3.2: 45.0 (#224)

Writing & Preference benchmarks
Benchmark	Mistral Large 4	Mistral Small 3.2
LMArena Text	1427	—
LMArena Creative Writing	1361	—
EQ-Bench Creative Writing	—	1255
LMArena Multi-Turn	1424	—

Frequently asked questions

Is Mistral Large 4 better than Mistral Small 3.2?

Which is cheaper, Mistral Large 4 or Mistral Small 3.2?

Mistral Small 3.2 is cheaper. It lists at $0.0938 per million input tokens and $0.25 per million output tokens; Mistral Large 4 lists at $0.68 and $2.09.

Which has the bigger context window?

Mistral Large 4 does, with 1.05M tokens against 256K.

How many benchmarks do Mistral Large 4 and Mistral Small 3.2 share?

0 benchmarks have published results for both models. Mistral Large 4 has 15 scored results on Noometry and Mistral Small 3.2 has 6.