Model comparison

Llama 3.2 3B vs MiniMax-M2.1

MiniMax-M2.1 is the stronger model overall, scoring 38.9 to 28.9 on the Noometry Index. Llama 3.2 3B costs 4.4× less per token, which makes it the better buy when MiniMax-M2.1's lead doesn't matter for your workload.

Last verified October 12, 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 MiniMax-M2.1 in 8 categories; 9 gaps are clear of the uncertainty.
The widest gap is in writing & preference, where MiniMax-M2.1 leads 58.3 to 24.7.
Llama 3.2 3B is cheaper at $0.05 / $0.33 per million input/output tokens, against $0.30 / $1.20 for MiniMax-M2.1.
MiniMax-M2.1 accepts more context: 205K tokens versus 131K.

Side by side

Llama 3.2 3B and MiniMax-M2.1 specifications
	Llama 3.2 3B	MiniMax-M2.1
Provider	Meta	MiniMax
Noometry Index	28.9	38.9
Released	2024-09-24	2025-12-23
Weights	Open	Open
Context window	131K	205K
Max output	118K	131K
Input $ / M tokens	$0.05	$0.30
Output $ / M tokens	$0.33	$1.20
Results tracked	18	22

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

Category by category

Coding MiniMax-M2.1 leads

Llama 3.2 3B: 27.6 (#319), MiniMax-M2.1: 40.4 (#143)

Coding benchmarks
Benchmark	Llama 3.2 3B	MiniMax-M2.1
LMArena Coding	1098	1421
LMArena WebDev	—	1384
BigCodeBench Instruct	23.4%	—
BigCodeBench Complete	28.3%	—
ALE-Bench	—	623.83

Agentic & Tool Use MiniMax-M2.1 leads

Llama 3.2 3B: 20.1 (#143), MiniMax-M2.1: 27.9 (#98)

Agentic & Tool Use benchmarks
Benchmark	Llama 3.2 3B	MiniMax-M2.1
Terminal-Bench	—	36.6%
Berkeley Function Calling Leaderboard	21.9%	—
BALROG	10.1%	—

Reasoning Llama 3.2 3B leads

Llama 3.2 3B: 21.0 (#228), MiniMax-M2.1: 16.6 (#302)

Reasoning benchmarks
Benchmark	Llama 3.2 3B	MiniMax-M2.1
LMArena Hard Prompts	1095	1411
NYT Connections (extended)	—	11.2%

Math MiniMax-M2.1 leads

Llama 3.2 3B: 32.4 (#214), MiniMax-M2.1: 38.3 (#138)

Math benchmarks
Benchmark	Llama 3.2 3B	MiniMax-M2.1
LMArena Math	1126	1397

Knowledge MiniMax-M2.1 leads

Llama 3.2 3B: 29.7 (#235), MiniMax-M2.1: 38.3 (#147)

Knowledge benchmarks
Benchmark	Llama 3.2 3B	MiniMax-M2.1
LMArena Expert	1090	1431
Vectara Hallucination Rate	—	11.8%

Multilingual MiniMax-M2.1 leads

Llama 3.2 3B: 26.2 (#281), MiniMax-M2.1: 50.0 (#128)

Multilingual benchmarks
Benchmark	Llama 3.2 3B	MiniMax-M2.1
LMArena Non-English	1019	1378
LMArena Chinese	1017	1430
LMArena German	1056	1381
LMArena Russian	949	1387
LMArena French	—	1404
LMArena Japanese	—	1287
LMArena Korean	—	1298
LMArena Spanish	—	1397

Instruction Following MiniMax-M2.1 leads

Llama 3.2 3B: 56.0 (#275), MiniMax-M2.1: 73.8 (#112)

Instruction Following benchmarks
Benchmark	Llama 3.2 3B	MiniMax-M2.1
LMArena Instruction Following	1089	1400

Long Context MiniMax-M2.1 leads

Llama 3.2 3B: 33.4 (#261), MiniMax-M2.1: 43.2 (#101)

Long Context benchmarks
Benchmark	Llama 3.2 3B	MiniMax-M2.1
LMArena Longer Query	1100	1416

Writing & Preference MiniMax-M2.1 leads

Llama 3.2 3B: 24.7 (#307), MiniMax-M2.1: 58.3 (#120)

Writing & Preference benchmarks
Benchmark	Llama 3.2 3B	MiniMax-M2.1
LMArena Text	1110	1392
LMArena Creative Writing	1094	1361
LMArena Multi-Turn	1105	1396
EQ-Bench Creative Writing	595	—

Frequently asked questions

Is Llama 3.2 3B better than MiniMax-M2.1?

Which is cheaper, Llama 3.2 3B or MiniMax-M2.1?

Llama 3.2 3B is cheaper. It lists at $0.05 per million input tokens and $0.33 per million output tokens; MiniMax-M2.1 lists at $0.30 and $1.20.

Is Llama 3.2 3B or MiniMax-M2.1 better for coding?

MiniMax-M2.1 scores higher on coding benchmarks: 40.4 versus 27.6 in the Noometry coding category.

Which has the bigger context window?

MiniMax-M2.1 does, with 205K tokens against 131K.

How many benchmarks do Llama 3.2 3B and MiniMax-M2.1 share?

13 benchmarks have published results for both models. Llama 3.2 3B has 18 scored results on Noometry and MiniMax-M2.1 has 22.