Model comparison

Llama 3.2 1B vs Llama 3.2 3B

Llama 3.2 3B is the stronger model overall, scoring 28.4 to 19.9 on the Noometry Index. Llama 3.2 1B costs 1.7× less per token, which makes it the better buy when Llama 3.2 3B's lead doesn't matter for your workload.

Last verified October 10, 2026. 18 shared benchmarks.

Llama 3.2 1B

Summary

They share 18 benchmarks with published results for both. Llama 3.2 1B scores higher in 0 categories and Llama 3.2 3B in 9 categories; 9 gaps are clear of the uncertainty.
The widest gap is in knowledge, where Llama 3.2 3B leads 29.1 to 7.2.
The biggest single-benchmark swing is BigCodeBench Complete: 11.3% for Llama 3.2 1B and 28.3% for Llama 3.2 3B.
Llama 3.2 1B is cheaper at $0.027 / $0.20 per million input/output tokens, against $0.05 / $0.33 for Llama 3.2 3B.
Llama 3.2 3B accepts more context: 131K tokens versus 60K.

Side by side

Llama 3.2 1B and Llama 3.2 3B specifications
	Llama 3.2 1B	Llama 3.2 3B
Provider	Meta	Meta
Noometry Index	19.9	28.4
Released	2024-09-24	2024-09-24
Weights	Open	Open
Context window	60K	131K
Max output	54K	118K
Input $ / M tokens	$0.027	$0.05
Output $ / M tokens	$0.20	$0.33
Results tracked	22	18

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

Category by category

Coding Llama 3.2 3B leads

Llama 3.2 1B: 20.6 (#333), Llama 3.2 3B: 27.1 (#314)

Coding benchmarks
Benchmark	Llama 3.2 1B	Llama 3.2 3B
BigCodeBench Instruct	8.2%	23.4%
LMArena Coding	1071	1098
BigCodeBench Complete	11.3%	28.3%

Agentic & Tool Use Llama 3.2 3B leads

Llama 3.2 1B: 14.5 (#142), Llama 3.2 3B: 19.9 (#135)

Agentic & Tool Use benchmarks
Benchmark	Llama 3.2 1B	Llama 3.2 3B
Berkeley Function Calling Leaderboard	10.8%	21.9%
BALROG	6.6%	10.1%

Reasoning Llama 3.2 3B leads

Llama 3.2 1B: 15.6 (#304), Llama 3.2 3B: 20.1 (#225)

Reasoning benchmarks
Benchmark	Llama 3.2 1B	Llama 3.2 3B
LMArena Hard Prompts	1044	1095
Chess Puzzles	0%	—
Epoch Capabilities Index	101.95	—

Math Llama 3.2 3B leads

Llama 3.2 1B: 9.7 (#308), Llama 3.2 3B: 29.9 (#213)

Math benchmarks
Benchmark	Llama 3.2 1B	Llama 3.2 3B
LMArena Math	1086	1126
OTIS Mock AIME 2024-2025	0.6%	—

Knowledge Llama 3.2 3B leads

Llama 3.2 1B: 7.2 (#307), Llama 3.2 3B: 29.1 (#232)

Knowledge benchmarks
Benchmark	Llama 3.2 1B	Llama 3.2 3B
LMArena Expert	1007	1090
GPQA Diamond	23.9%	—

Multilingual Llama 3.2 3B leads

Llama 3.2 1B: 23.9 (#287), Llama 3.2 3B: 26.4 (#276)

Multilingual benchmarks
Benchmark	Llama 3.2 1B	Llama 3.2 3B
LMArena Non-English	973	1019
LMArena Chinese	958	1017
LMArena German	1014	1056
LMArena Russian	941	949

Instruction Following Llama 3.2 3B leads

Llama 3.2 1B: 52.6 (#285), Llama 3.2 3B: 56.3 (#270)

Instruction Following benchmarks
Benchmark	Llama 3.2 1B	Llama 3.2 3B
LMArena Instruction Following	1031	1089

Long Context Llama 3.2 3B leads

Llama 3.2 1B: 31.9 (#269), Llama 3.2 3B: 33.4 (#256)

Long Context benchmarks
Benchmark	Llama 3.2 1B	Llama 3.2 3B
LMArena Longer Query	1050	1101

Writing & Preference Llama 3.2 3B leads

Llama 3.2 1B: 21.4 (#305), Llama 3.2 3B: 24.9 (#302)

Writing & Preference benchmarks
Benchmark	Llama 3.2 1B	Llama 3.2 3B
LMArena Text	1055	1110
LMArena Creative Writing	1033	1094
EQ-Bench Creative Writing	200	595
LMArena Multi-Turn	1030	1105

Frequently asked questions

Is Llama 3.2 1B better than Llama 3.2 3B?

Which is cheaper, Llama 3.2 1B or Llama 3.2 3B?

Llama 3.2 1B is cheaper. It lists at $0.027 per million input tokens and $0.20 per million output tokens; Llama 3.2 3B lists at $0.05 and $0.33.

Is Llama 3.2 1B or Llama 3.2 3B better for coding?

Llama 3.2 3B scores higher on coding benchmarks: 27.1 versus 20.6 in the Noometry coding category.

Which has the bigger context window?

Llama 3.2 3B does, with 131K tokens against 60K.

How many benchmarks do Llama 3.2 1B and Llama 3.2 3B share?

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