Model comparison

Llama 3.2 3B vs Magistral Medium

Magistral Medium is the stronger model overall, scoring 34.8 to 28.4 on the Noometry Index. Llama 3.2 3B costs 23× less per token, which makes it the better buy when Magistral Medium's lead doesn't matter for your workload.

Last verified October 10, 2026. 13 shared benchmarks.

Llama 3.2 3B

Summary

They share 13 benchmarks with published results for both. Llama 3.2 3B scores higher in 1 category and Magistral Medium in 7 categories; 8 gaps are clear of the uncertainty.
The widest gap is in writing & preference, where Magistral Medium leads 46.5 to 24.9.
Llama 3.2 3B is cheaper at $0.05 / $0.33 per million input/output tokens, against $2 / $5 for Magistral Medium.
Llama 3.2 3B accepts more context: 131K tokens versus 128K.

Side by side

Llama 3.2 3B and Magistral Medium specifications
	Llama 3.2 3B	Magistral Medium
Provider	Meta	Mistral AI
Noometry Index	28.4	34.8
Released	2024-09-24	2025-03-17
Weights	Open	Open
Context window	131K	128K
Max output	118K	16K
Input $ / M tokens	$0.05	$2
Output $ / M tokens	$0.33	$5
Results tracked	18	22

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

Category by category

Coding Magistral Medium leads

Llama 3.2 3B: 27.1 (#314), Magistral Medium: 38.6 (#161)

Coding benchmarks
Benchmark	Llama 3.2 3B	Magistral Medium
LMArena Coding	1098	1319
SciCode	—	39.2%
BigCodeBench Instruct	23.4%	—
BigCodeBench Complete	28.3%	—

Agentic & Tool Use Not comparable

Llama 3.2 3B: 19.9 (#135), Magistral Medium: —

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

Reasoning Llama 3.2 3B leads

Llama 3.2 3B: 20.1 (#225), Magistral Medium: 8.7 (#342)

Reasoning benchmarks
Benchmark	Llama 3.2 3B	Magistral Medium
LMArena Hard Prompts	1095	1267
ARC-AGI-2	—	0%
Kagi LLM Benchmark	—	16.2%
ARC-AGI-1	—	6.1%
CritPt	—	0.3%

Math Magistral Medium leads

Llama 3.2 3B: 29.9 (#213), Magistral Medium: 32.4 (#187)

Math benchmarks
Benchmark	Llama 3.2 3B	Magistral Medium
LMArena Math	1126	1249

Knowledge Magistral Medium leads

Llama 3.2 3B: 29.1 (#232), Magistral Medium: 32.9 (#199)

Knowledge benchmarks
Benchmark	Llama 3.2 3B	Magistral Medium
LMArena Expert	1090	1222

Multilingual Magistral Medium leads

Llama 3.2 3B: 26.4 (#276), Magistral Medium: 39.8 (#219)

Multilingual benchmarks
Benchmark	Llama 3.2 3B	Magistral Medium
LMArena Non-English	1019	1232
LMArena Chinese	1017	1225
LMArena German	1056	1248
LMArena Russian	949	1224
LMArena French	—	1268
LMArena Japanese	—	1176
LMArena Korean	—	1125
LMArena Spanish	—	1269

Instruction Following Magistral Medium leads

Llama 3.2 3B: 56.3 (#270), Magistral Medium: 66.2 (#207)

Instruction Following benchmarks
Benchmark	Llama 3.2 3B	Magistral Medium
LMArena Instruction Following	1089	1254

Long Context Magistral Medium leads

Llama 3.2 3B: 33.4 (#256), Magistral Medium: 39.3 (#178)

Long Context benchmarks
Benchmark	Llama 3.2 3B	Magistral Medium
LMArena Longer Query	1101	1295

Writing & Preference Magistral Medium leads

Llama 3.2 3B: 24.9 (#302), Magistral Medium: 46.5 (#214)

Writing & Preference benchmarks
Benchmark	Llama 3.2 3B	Magistral Medium
LMArena Text	1110	1255
LMArena Creative Writing	1094	1245
LMArena Multi-Turn	1105	1275
EQ-Bench Creative Writing	595	—

Frequently asked questions

Is Llama 3.2 3B better than Magistral Medium?

Which is cheaper, Llama 3.2 3B or Magistral Medium?

Llama 3.2 3B is cheaper. It lists at $0.05 per million input tokens and $0.33 per million output tokens; Magistral Medium lists at $2 and $5.

Is Llama 3.2 3B or Magistral Medium better for coding?

Magistral Medium scores higher on coding benchmarks: 38.6 versus 27.1 in the Noometry coding category.

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 Magistral Medium share?

13 benchmarks have published results for both models. Llama 3.2 3B has 18 scored results on Noometry and Magistral Medium has 22.