Model comparison

Llama 3.2 3B vs MiniMax-M3

MiniMax-M3 is the stronger model overall, scoring 43.8 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-M3's lead doesn't matter for your workload.

Last verified October 11, 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 0 categories and MiniMax-M3 in 9 categories; 9 gaps are clear of the uncertainty.
The widest gap is in writing & preference, where MiniMax-M3 leads 62.1 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-M3.
MiniMax-M3 accepts more context: 1M tokens versus 131K.

Side by side

Llama 3.2 3B and MiniMax-M3 specifications
	Llama 3.2 3B	MiniMax-M3
Provider	Meta	MiniMax
Noometry Index	28.9	43.8
Released	2024-09-24	2026-06-01
Weights	Open	Open
Context window	131K	1M
Max output	118K	512K
Input $ / M tokens	$0.05	$0.30
Output $ / M tokens	$0.33	$1.20
Results tracked	18	41

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

Category by category

Coding MiniMax-M3 leads

Llama 3.2 3B: 27.6 (#319), MiniMax-M3: 41.8 (#118)

Coding benchmarks
Benchmark	Llama 3.2 3B	MiniMax-M3
LMArena Coding	1098	1469
FrontierCode	—	14.7%
LMArena WebDev	—	1482
SciCode	—	47.1%
BigCodeBench Instruct	23.4%	—
BigCodeBench Complete	28.3%	—
ALE-Bench	—	640.02

Agentic & Tool Use MiniMax-M3 leads

Llama 3.2 3B: 20.1 (#143), MiniMax-M3: 22.6 (#130)

Agentic & Tool Use benchmarks
Benchmark	Llama 3.2 3B	MiniMax-M3
APEX-Agents	—	37.7%
Berkeley Function Calling Leaderboard	21.9%	—
OSWorld 2.0	—	4.6%
BALROG	10.1%	—
GBAEval	—	0.9%
Vending-Bench 2	—	2,158

Reasoning MiniMax-M3 leads

Llama 3.2 3B: 21.0 (#228), MiniMax-M3: 30.1 (#87)

Reasoning benchmarks
Benchmark	Llama 3.2 3B	MiniMax-M3
LMArena Hard Prompts	1095	1447
SimpleBench	—	45.8%
NYT Connections (extended)	—	65.1%
CritPt	—	3.7%
Chess Puzzles	—	14%
Mystery Game Puzzles	—	8%
DTBench	—	78.9%
LMCA	—	33.7%
Surface Evolver Bench	—	55%
Epoch Capabilities Index	—	146.95
ForecastBench	—	61.4

Math MiniMax-M3 leads

Llama 3.2 3B: 32.4 (#214), MiniMax-M3: 40.0 (#95)

Math benchmarks
Benchmark	Llama 3.2 3B	MiniMax-M3
LMArena Math	1126	1429
OTIS Mock AIME 2024-2025	—	71.1%
ProofBench	—	18%

Knowledge MiniMax-M3 leads

Llama 3.2 3B: 29.7 (#235), MiniMax-M3: 58.4 (#35)

Knowledge benchmarks
Benchmark	Llama 3.2 3B	MiniMax-M3
LMArena Expert	1090	1461
GPQA Diamond	—	90.9%

Multimodal Not comparable

Llama 3.2 3B: —, MiniMax-M3: 40.2 (#51)

Multimodal benchmarks
Benchmark	Llama 3.2 3B	MiniMax-M3
LMArena Vision	—	1253
LMArena Document	—	1435

Multilingual MiniMax-M3 leads

Llama 3.2 3B: 26.2 (#281), MiniMax-M3: 53.0 (#75)

Multilingual benchmarks
Benchmark	Llama 3.2 3B	MiniMax-M3
LMArena Non-English	1019	1420
LMArena Chinese	1017	1463
LMArena German	1056	1426
LMArena Russian	949	1428
LMArena French	—	1447
LMArena Japanese	—	1381
LMArena Korean	—	1372
LMArena Spanish	—	1432

Instruction Following MiniMax-M3 leads

Llama 3.2 3B: 56.0 (#275), MiniMax-M3: 75.5 (#62)

Instruction Following benchmarks
Benchmark	Llama 3.2 3B	MiniMax-M3
LMArena Instruction Following	1089	1433

Long Context MiniMax-M3 leads

Llama 3.2 3B: 33.4 (#261), MiniMax-M3: 44.2 (#72)

Long Context benchmarks
Benchmark	Llama 3.2 3B	MiniMax-M3
LMArena Longer Query	1100	1445

Writing & Preference MiniMax-M3 leads

Llama 3.2 3B: 24.7 (#307), MiniMax-M3: 62.1 (#83)

Writing & Preference benchmarks
Benchmark	Llama 3.2 3B	MiniMax-M3
LMArena Text	1110	1433
LMArena Creative Writing	1094	1404
LMArena Multi-Turn	1105	1442
EQ-Bench Creative Writing	595	—
EQ-Bench 4	—	1150

Frequently asked questions

Is Llama 3.2 3B better than MiniMax-M3?

Which is cheaper, Llama 3.2 3B or MiniMax-M3?

Llama 3.2 3B is cheaper. It lists at $0.05 per million input tokens and $0.33 per million output tokens; MiniMax-M3 lists at $0.30 and $1.20.

Is Llama 3.2 3B or MiniMax-M3 better for coding?

MiniMax-M3 scores higher on coding benchmarks: 41.8 versus 27.6 in the Noometry coding category.

Which has the bigger context window?

MiniMax-M3 does, with 1M tokens against 131K.

How many benchmarks do Llama 3.2 3B and MiniMax-M3 share?

13 benchmarks have published results for both models. Llama 3.2 3B has 18 scored results on Noometry and MiniMax-M3 has 41.