Model comparison

Llama 3.2 3B vs MiMo-V2.6-Pro

MiMo-V2.6-Pro is the stronger model overall, scoring 46.7 to 28.4 on the Noometry Index. Llama 3.2 3B costs 4.5× less per token, which makes it the better buy when MiMo-V2.6-Pro's lead doesn't matter for your workload.

Last verified October 10, 2026. 12 shared benchmarks.

Llama 3.2 3B

Summary

They share 12 benchmarks with published results for both. Llama 3.2 3B scores higher in 0 categories and MiMo-V2.6-Pro in 8 categories; 8 gaps are clear of the uncertainty.
The widest gap is in writing & preference, where MiMo-V2.6-Pro leads 66.9 to 24.9.
Llama 3.2 3B is cheaper at $0.05 / $0.33 per million input/output tokens, against $0.43 / $0.87 for MiMo-V2.6-Pro.
MiMo-V2.6-Pro accepts more context: 1.05M tokens versus 131K.

Side by side

Llama 3.2 3B and MiMo-V2.6-Pro specifications
	Llama 3.2 3B	MiMo-V2.6-Pro
Provider	Meta	Xiaomi
Noometry Index	28.4	46.7
Released	2024-09-24	2026-09-22
Weights	Open	Open
Context window	131K	1.05M
Max output	118K	131K
Input $ / M tokens	$0.05	$0.43
Output $ / M tokens	$0.33	$0.87
Results tracked	18	14

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

Category by category

Coding MiMo-V2.6-Pro leads

Llama 3.2 3B: 27.1 (#314), MiMo-V2.6-Pro: 53.2 (#27)

Coding benchmarks
Benchmark	Llama 3.2 3B	MiMo-V2.6-Pro
LMArena Coding	1098	1538
LMArena WebDev	—	1618
BigCodeBench Instruct	23.4%	—
BigCodeBench Complete	28.3%	—

Agentic & Tool Use Not comparable

Llama 3.2 3B: 19.9 (#135), MiMo-V2.6-Pro: —

Agentic & Tool Use benchmarks
Benchmark	Llama 3.2 3B	MiMo-V2.6-Pro
Berkeley Function Calling Leaderboard	21.9%	—
BALROG	10.1%	—

Reasoning MiMo-V2.6-Pro leads

Llama 3.2 3B: 20.1 (#225), MiMo-V2.6-Pro: 30.4 (#76)

Reasoning benchmarks
Benchmark	Llama 3.2 3B	MiMo-V2.6-Pro
LMArena Hard Prompts	1095	1511

Math MiMo-V2.6-Pro leads

Llama 3.2 3B: 29.9 (#213), MiMo-V2.6-Pro: 37.9 (#91)

Math benchmarks
Benchmark	Llama 3.2 3B	MiMo-V2.6-Pro
LMArena Math	1126	1497

Knowledge MiMo-V2.6-Pro leads

Llama 3.2 3B: 29.1 (#232), MiMo-V2.6-Pro: 43.0 (#85)

Knowledge benchmarks
Benchmark	Llama 3.2 3B	MiMo-V2.6-Pro
LMArena Expert	1090	1548

Multimodal Not comparable

Llama 3.2 3B: —, MiMo-V2.6-Pro: 40.2 (#40)

Multimodal benchmarks
Benchmark	Llama 3.2 3B	MiMo-V2.6-Pro
LMArena Vision	—	1265

Multilingual MiMo-V2.6-Pro leads

Llama 3.2 3B: 26.4 (#276), MiMo-V2.6-Pro: 57.0 (#15)

Multilingual benchmarks
Benchmark	Llama 3.2 3B	MiMo-V2.6-Pro
LMArena Non-English	1019	1474
LMArena Chinese	1017	1532
LMArena Russian	949	1481
LMArena German	1056	—

Instruction Following MiMo-V2.6-Pro leads

Llama 3.2 3B: 56.3 (#270), MiMo-V2.6-Pro: 78.2 (#10)

Instruction Following benchmarks
Benchmark	Llama 3.2 3B	MiMo-V2.6-Pro
LMArena Instruction Following	1089	1490

Long Context MiMo-V2.6-Pro leads

Llama 3.2 3B: 33.4 (#256), MiMo-V2.6-Pro: 46.0 (#26)

Long Context benchmarks
Benchmark	Llama 3.2 3B	MiMo-V2.6-Pro
LMArena Longer Query	1101	1500

Writing & Preference MiMo-V2.6-Pro leads

Llama 3.2 3B: 24.9 (#302), MiMo-V2.6-Pro: 66.9 (#32)

Writing & Preference benchmarks
Benchmark	Llama 3.2 3B	MiMo-V2.6-Pro
LMArena Text	1110	1491
LMArena Creative Writing	1094	1465
LMArena Multi-Turn	1105	1463
EQ-Bench Creative Writing	595	—

Frequently asked questions

Is Llama 3.2 3B better than MiMo-V2.6-Pro?

Which is cheaper, Llama 3.2 3B or MiMo-V2.6-Pro?

Llama 3.2 3B is cheaper. It lists at $0.05 per million input tokens and $0.33 per million output tokens; MiMo-V2.6-Pro lists at $0.43 and $0.87.

Is Llama 3.2 3B or MiMo-V2.6-Pro better for coding?

MiMo-V2.6-Pro scores higher on coding benchmarks: 53.2 versus 27.1 in the Noometry coding category.

Which has the bigger context window?

MiMo-V2.6-Pro does, with 1.05M tokens against 131K.

How many benchmarks do Llama 3.2 3B and MiMo-V2.6-Pro share?

12 benchmarks have published results for both models. Llama 3.2 3B has 18 scored results on Noometry and MiMo-V2.6-Pro has 14.