Model comparison

Llama 3.2 1B vs Ministral 8B

Ministral 8B is the stronger model overall, scoring 27.8 to 19.9 on the Noometry Index.

Last verified October 10, 2026. 14 shared benchmarks.

Summary

They share 14 benchmarks with published results for both. Llama 3.2 1B scores higher in 0 categories and Ministral 8B in 9 categories; 9 gaps are clear of the uncertainty.
The widest gap is in writing & preference, where Ministral 8B leads 39.8 to 21.4.
Llama 3.2 1B is cheaper at $0.027 / $0.20 per million input/output tokens, against $0.10 / $0.10 for Ministral 8B.
Ministral 8B accepts more context: 128K tokens versus 60K.

Side by side

Llama 3.2 1B and Ministral 8B specifications
	Llama 3.2 1B	Ministral 8B
Provider	Meta	Mistral AI
Noometry Index	19.9	27.8
Released	2024-09-24	2024-10-01
Weights	Open	Open
Context window	60K	128K
Max output	54K	128K
Input $ / M tokens	$0.027	$0.10
Output $ / M tokens	$0.20	$0.10
Results tracked	22	17

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

Category by category

Coding Ministral 8B leads

Llama 3.2 1B: 20.6 (#333), Ministral 8B: 34.4 (#226)

Coding benchmarks
Benchmark	Llama 3.2 1B	Ministral 8B
LMArena Coding	1071	1202
BigCodeBench Instruct	8.2%	—
BigCodeBench Complete	11.3%	—

Agentic & Tool Use Ministral 8B leads

Llama 3.2 1B: 14.5 (#142), Ministral 8B: 16.2 (#140)

Agentic & Tool Use benchmarks
Benchmark	Llama 3.2 1B	Ministral 8B
Berkeley Function Calling Leaderboard	10.8%	11.1%
BALROG	6.6%	—

Reasoning Ministral 8B leads

Llama 3.2 1B: 15.6 (#304), Ministral 8B: 17.7 (#279)

Reasoning benchmarks
Benchmark	Llama 3.2 1B	Ministral 8B
LMArena Hard Prompts	1044	1191
Chess Puzzles	0%	—
DTBench	—	45.7%
Epoch Capabilities Index	101.95	—

Math Ministral 8B leads

Llama 3.2 1B: 9.7 (#308), Ministral 8B: 23.7 (#262)

Math benchmarks
Benchmark	Llama 3.2 1B	Ministral 8B
LMArena Math	1086	1188
OTIS Mock AIME 2024-2025	0.6%	—
MATH Level 5	—	14.9%

Knowledge Ministral 8B leads

Llama 3.2 1B: 7.2 (#307), Ministral 8B: 12.5 (#292)

Knowledge benchmarks
Benchmark	Llama 3.2 1B	Ministral 8B
GPQA Diamond	23.9%	27.1%
LMArena Expert	1007	1170
Vectara Hallucination Rate	—	7.4%

Multilingual Ministral 8B leads

Llama 3.2 1B: 23.9 (#287), Ministral 8B: 35.3 (#242)

Multilingual benchmarks
Benchmark	Llama 3.2 1B	Ministral 8B
LMArena Non-English	973	1165
LMArena Chinese	958	1193
LMArena Russian	941	1195
LMArena German	1014	—

Instruction Following Ministral 8B leads

Llama 3.2 1B: 52.6 (#285), Ministral 8B: 60.7 (#245)

Instruction Following benchmarks
Benchmark	Llama 3.2 1B	Ministral 8B
LMArena Instruction Following	1031	1161

Long Context Ministral 8B leads

Llama 3.2 1B: 31.9 (#269), Ministral 8B: 36.7 (#222)

Long Context benchmarks
Benchmark	Llama 3.2 1B	Ministral 8B
LMArena Longer Query	1050	1212

Writing & Preference Ministral 8B leads

Llama 3.2 1B: 21.4 (#305), Ministral 8B: 39.8 (#241)

Writing & Preference benchmarks
Benchmark	Llama 3.2 1B	Ministral 8B
LMArena Text	1055	1191
LMArena Creative Writing	1033	1175
LMArena Multi-Turn	1030	1166
EQ-Bench Creative Writing	200	—

Frequently asked questions

Is Llama 3.2 1B better than Ministral 8B?

Ministral 8B is the stronger model overall, scoring 27.8 to 19.9 on the Noometry Index.

Which is cheaper, Llama 3.2 1B or Ministral 8B?

Llama 3.2 1B is cheaper. It lists at $0.027 per million input tokens and $0.20 per million output tokens; Ministral 8B lists at $0.10 and $0.10.

Is Llama 3.2 1B or Ministral 8B better for coding?

Ministral 8B scores higher on coding benchmarks: 34.4 versus 20.6 in the Noometry coding category.

Which has the bigger context window?

Ministral 8B does, with 128K tokens against 60K.

How many benchmarks do Llama 3.2 1B and Ministral 8B share?

14 benchmarks have published results for both models. Llama 3.2 1B has 22 scored results on Noometry and Ministral 8B has 17.