Model comparison

Llama 3.2 3B vs Pixtral Large

Pixtral Large is the stronger model overall, scoring 32.2 to 28.9 on the Noometry Index. Llama 3.2 3B costs 25× less per token, which makes it the better buy when Pixtral Large's lead doesn't matter for your workload.

Last verified October 11, 2026. 1 shared benchmarks.

Llama 3.2 3B

Summary

They share 1 benchmark with published results for both. Llama 3.2 3B scores higher in 0 categories and Pixtral Large in 2 categories; one gap is clear of the uncertainty.
The widest gap is in writing & preference, where Pixtral Large leads 32.9 to 24.7.
Llama 3.2 3B is cheaper at $0.05 / $0.33 per million input/output tokens, against $2 / $6 for Pixtral Large.
Llama 3.2 3B accepts more context: 131K tokens versus 128K.

Side by side

Llama 3.2 3B and Pixtral Large specifications
	Llama 3.2 3B	Pixtral Large
Provider	Meta	Mistral AI
Noometry Index	28.9	32.2
Released	2024-09-24	2024-11-01
Weights	Open	Open
Context window	131K	128K
Max output	118K	128K
Input $ / M tokens	$0.05	$2
Output $ / M tokens	$0.33	$6
Results tracked	18	3

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

Category by category

Coding Not comparable

Llama 3.2 3B: 27.6 (#319), Pixtral Large: —

Coding benchmarks
Benchmark	Llama 3.2 3B	Pixtral Large
BigCodeBench Instruct	23.4%	—
LMArena Coding	1098	—
BigCodeBench Complete	28.3%	—

Agentic & Tool Use Not comparable

Llama 3.2 3B: 20.1 (#143), Pixtral Large: —

Agentic & Tool Use benchmarks
Benchmark	Llama 3.2 3B	Pixtral Large
Berkeley Function Calling Leaderboard	21.9%	—
BALROG	10.1%	—

Reasoning Too close to call

Llama 3.2 3B: 21.0 (#228), Pixtral Large: 21.7 (#218)

Reasoning benchmarks
Benchmark	Llama 3.2 3B	Pixtral Large
EnigmaEval	—	0.8%
LMArena Hard Prompts	1095	—

Math Not comparable

Llama 3.2 3B: 32.4 (#214), Pixtral Large: —

Math benchmarks
Benchmark	Llama 3.2 3B	Pixtral Large
LMArena Math	1126	—

Knowledge Not comparable

Llama 3.2 3B: 29.7 (#235), Pixtral Large: —

Knowledge benchmarks
Benchmark	Llama 3.2 3B	Pixtral Large
LMArena Expert	1090	—

Multimodal Not comparable

Llama 3.2 3B: —, Pixtral Large: 30.6 (#111)

Multimodal benchmarks
Benchmark	Llama 3.2 3B	Pixtral Large
LMArena Vision	—	1089

Multilingual Not comparable

Llama 3.2 3B: 26.2 (#281), Pixtral Large: —

Multilingual benchmarks
Benchmark	Llama 3.2 3B	Pixtral Large
LMArena Non-English	1019	—
LMArena Chinese	1017	—
LMArena German	1056	—
LMArena Russian	949	—

Instruction Following Not comparable

Llama 3.2 3B: 56.0 (#275), Pixtral Large: —

Instruction Following benchmarks
Benchmark	Llama 3.2 3B	Pixtral Large
LMArena Instruction Following	1089	—

Long Context Not comparable

Llama 3.2 3B: 33.4 (#261), Pixtral Large: —

Long Context benchmarks
Benchmark	Llama 3.2 3B	Pixtral Large
LMArena Longer Query	1100	—

Writing & Preference Pixtral Large leads

Llama 3.2 3B: 24.7 (#307), Pixtral Large: 32.9 (#278)

Writing & Preference benchmarks
Benchmark	Llama 3.2 3B	Pixtral Large
EQ-Bench Creative Writing	595	988
LMArena Text	1110	—
LMArena Creative Writing	1094	—
LMArena Multi-Turn	1105	—

Frequently asked questions

Is Llama 3.2 3B better than Pixtral Large?

Which is cheaper, Llama 3.2 3B or Pixtral Large?

Llama 3.2 3B is cheaper. It lists at $0.05 per million input tokens and $0.33 per million output tokens; Pixtral Large lists at $2 and $6.

Which has the bigger context window?

Llama 3.2 3B does, with 131K tokens against 128K.

How many benchmarks do Llama 3.2 3B and Pixtral Large share?

1 benchmark has published results for both models. Llama 3.2 3B has 18 scored results on Noometry and Pixtral Large has 3.