Model comparison

Llama 3.2 1B vs MiniMax-M2

MiniMax-M2 is the stronger model overall, scoring 37.4 to 20.1 on the Noometry Index. Llama 3.2 1B costs 7.4× less per token, which makes it the better buy when MiniMax-M2's lead doesn't matter for your workload.

Last verified October 11, 2026. 13 shared benchmarks.

Llama 3.2 1B

Summary

They share 13 benchmarks with published results for both. Llama 3.2 1B scores higher in 0 categories and MiniMax-M2 in 9 categories; 9 gaps are clear of the uncertainty.
The widest gap is in writing & preference, where MiniMax-M2 leads 53.0 to 21.3.
Llama 3.2 1B is cheaper at $0.027 / $0.20 per million input/output tokens, against $0.30 / $1.20 for MiniMax-M2.
MiniMax-M2 accepts more context: 205K tokens versus 60K.

Side by side

Llama 3.2 1B and MiniMax-M2 specifications
	Llama 3.2 1B	MiniMax-M2
Provider	Meta	MiniMax
Noometry Index	20.1	37.4
Released	2024-09-24	2025-10-27
Weights	Open	Open
Context window	60K	205K
Max output	54K	131K
Input $ / M tokens	$0.027	$0.30
Output $ / M tokens	$0.20	$1.20
Results tracked	22	21

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

Category by category

Coding MiniMax-M2 leads

Llama 3.2 1B: 21.1 (#338), MiniMax-M2: 39.3 (#159)

Coding benchmarks
Benchmark	Llama 3.2 1B	MiniMax-M2
LMArena Coding	1070	1370
SWE-bench Verified (bash only)	—	61%
LMArena WebDev	—	1297
BigCodeBench Instruct	8.2%	—
BigCodeBench Complete	11.3%	—

Agentic & Tool Use MiniMax-M2 leads

Llama 3.2 1B: 14.6 (#150), MiniMax-M2: 25.1 (#109)

Agentic & Tool Use benchmarks
Benchmark	Llama 3.2 1B	MiniMax-M2
Terminal-Bench	—	30%
Berkeley Function Calling Leaderboard	10.8%	—
BALROG	6.6%	—
Vending-Bench 2	—	160.6

Reasoning MiniMax-M2 leads

Llama 3.2 1B: 16.2 (#308), MiniMax-M2: 19.4 (#258)

Reasoning benchmarks
Benchmark	Llama 3.2 1B	MiniMax-M2
LMArena Hard Prompts	1044	1357
Kagi LLM Benchmark	—	57.8%
NYT Connections (extended)	—	14.8%
Chess Puzzles	0%	—
Epoch Capabilities Index	101.99	—

Math MiniMax-M2 leads

Llama 3.2 1B: 10.4 (#313), MiniMax-M2: 37.3 (#160)

Math benchmarks
Benchmark	Llama 3.2 1B	MiniMax-M2
LMArena Math	1086	1352
OTIS Mock AIME 2024-2025	0.6%	—

Knowledge MiniMax-M2 leads

Llama 3.2 1B: 7.2 (#312), MiniMax-M2: 37.0 (#163)

Knowledge benchmarks
Benchmark	Llama 3.2 1B	MiniMax-M2
LMArena Expert	1007	1337
GPQA Diamond	23.9%	—

Multilingual MiniMax-M2 leads

Llama 3.2 1B: 23.8 (#292), MiniMax-M2: 45.3 (#171)

Multilingual benchmarks
Benchmark	Llama 3.2 1B	MiniMax-M2
LMArena Non-English	973	1313
LMArena Chinese	959	1366
LMArena German	1014	1355
LMArena Russian	941	1331
LMArena French	—	1335
LMArena Spanish	—	1326

Instruction Following MiniMax-M2 leads

Llama 3.2 1B: 52.4 (#290), MiniMax-M2: 70.2 (#166)

Instruction Following benchmarks
Benchmark	Llama 3.2 1B	MiniMax-M2
LMArena Instruction Following	1031	1328

Long Context MiniMax-M2 leads

Llama 3.2 1B: 31.9 (#274), MiniMax-M2: 40.5 (#153)

Long Context benchmarks
Benchmark	Llama 3.2 1B	MiniMax-M2
LMArena Longer Query	1050	1331

Writing & Preference MiniMax-M2 leads

Llama 3.2 1B: 21.3 (#310), MiniMax-M2: 53.0 (#162)

Writing & Preference benchmarks
Benchmark	Llama 3.2 1B	MiniMax-M2
LMArena Text	1055	1340
LMArena Creative Writing	1033	1286
LMArena Multi-Turn	1030	1361
EQ-Bench Creative Writing	200	—

Frequently asked questions

Is Llama 3.2 1B better than MiniMax-M2?

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

Llama 3.2 1B is cheaper. It lists at $0.027 per million input tokens and $0.20 per million output tokens; MiniMax-M2 lists at $0.30 and $1.20.

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

MiniMax-M2 scores higher on coding benchmarks: 39.3 versus 21.1 in the Noometry coding category.

Which has the bigger context window?

MiniMax-M2 does, with 205K tokens against 60K.

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

13 benchmarks have published results for both models. Llama 3.2 1B has 22 scored results on Noometry and MiniMax-M2 has 21.