Model comparison

Llama 3.2 3B vs Ministral 8B

Llama 3.2 3B and Ministral 8B score almost the same on the Noometry Index (28.4 vs 27.8), so choose on price, context window or the category you care about most.

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 4 categories and Ministral 8B in 5 categories; 9 gaps are clear of the uncertainty.
The widest gap is in knowledge, where Llama 3.2 3B leads 29.1 to 12.5.
The biggest single-benchmark swing is Berkeley Function Calling Leaderboard: 21.9% for Llama 3.2 3B and 11.1% for Ministral 8B.
Ministral 8B is cheaper at $0.10 / $0.10 per million input/output tokens, against $0.05 / $0.33 for Llama 3.2 3B.
Llama 3.2 3B accepts more context: 131K tokens versus 128K.

Side by side

Llama 3.2 3B and Ministral 8B specifications
	Llama 3.2 3B	Ministral 8B
Provider	Meta	Mistral AI
Noometry Index	28.4	27.8
Released	2024-09-24	2024-10-01
Weights	Open	Open
Context window	131K	128K
Max output	118K	128K
Input $ / M tokens	$0.05	$0.10
Output $ / M tokens	$0.33	$0.10
Results tracked	18	17

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

Category by category

Coding Ministral 8B leads

Llama 3.2 3B: 27.1 (#314), Ministral 8B: 34.4 (#226)

Coding benchmarks
Benchmark	Llama 3.2 3B	Ministral 8B
LMArena Coding	1098	1202
BigCodeBench Instruct	23.4%	—
BigCodeBench Complete	28.3%	—

Agentic & Tool Use Llama 3.2 3B leads

Llama 3.2 3B: 19.9 (#135), Ministral 8B: 16.2 (#140)

Agentic & Tool Use benchmarks
Benchmark	Llama 3.2 3B	Ministral 8B
Berkeley Function Calling Leaderboard	21.9%	11.1%
BALROG	10.1%	—

Reasoning Llama 3.2 3B leads

Llama 3.2 3B: 20.1 (#225), Ministral 8B: 17.7 (#279)

Reasoning benchmarks
Benchmark	Llama 3.2 3B	Ministral 8B
LMArena Hard Prompts	1095	1191
DTBench	—	45.7%

Math Llama 3.2 3B leads

Llama 3.2 3B: 29.9 (#213), Ministral 8B: 23.7 (#262)

Math benchmarks
Benchmark	Llama 3.2 3B	Ministral 8B
LMArena Math	1126	1188
MATH Level 5	—	14.9%

Knowledge Llama 3.2 3B leads

Llama 3.2 3B: 29.1 (#232), Ministral 8B: 12.5 (#292)

Knowledge benchmarks
Benchmark	Llama 3.2 3B	Ministral 8B
LMArena Expert	1090	1170
GPQA Diamond	—	27.1%
Vectara Hallucination Rate	—	7.4%

Multilingual Ministral 8B leads

Llama 3.2 3B: 26.4 (#276), Ministral 8B: 35.3 (#242)

Multilingual benchmarks
Benchmark	Llama 3.2 3B	Ministral 8B
LMArena Non-English	1019	1165
LMArena Chinese	1017	1193
LMArena Russian	949	1195
LMArena German	1056	—

Instruction Following Ministral 8B leads

Llama 3.2 3B: 56.3 (#270), Ministral 8B: 60.7 (#245)

Instruction Following benchmarks
Benchmark	Llama 3.2 3B	Ministral 8B
LMArena Instruction Following	1089	1161

Long Context Ministral 8B leads

Llama 3.2 3B: 33.4 (#256), Ministral 8B: 36.7 (#222)

Long Context benchmarks
Benchmark	Llama 3.2 3B	Ministral 8B
LMArena Longer Query	1101	1212

Writing & Preference Ministral 8B leads

Llama 3.2 3B: 24.9 (#302), Ministral 8B: 39.8 (#241)

Writing & Preference benchmarks
Benchmark	Llama 3.2 3B	Ministral 8B
LMArena Text	1110	1191
LMArena Creative Writing	1094	1175
LMArena Multi-Turn	1105	1166
EQ-Bench Creative Writing	595	—

Frequently asked questions

Is Llama 3.2 3B better than Ministral 8B?

Llama 3.2 3B and Ministral 8B score almost the same on the Noometry Index (28.4 vs 27.8), so choose on price, context window or the category you care about most.

Which is cheaper, Llama 3.2 3B or Ministral 8B?

Ministral 8B is cheaper. It lists at $0.10 per million input tokens and $0.10 per million output tokens; Llama 3.2 3B lists at $0.05 and $0.33.

Is Llama 3.2 3B or Ministral 8B better for coding?

Ministral 8B scores higher on coding benchmarks: 34.4 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 Ministral 8B share?

13 benchmarks have published results for both models. Llama 3.2 3B has 18 scored results on Noometry and Ministral 8B has 17.