Model comparison

Gemma 3 12B vs Llama 3.2 3B

Gemma 3 12B is the stronger model overall, scoring 32.1 to 28.9 on the Noometry Index.

Last verified October 10, 2026. 14 shared benchmarks.

Gemma 3 12B

Google

32.1

Rank #262 Confirmed

Llama 3.2 3B

Summary

They share 14 benchmarks with published results for both. Gemma 3 12B scores higher in 6 categories and Llama 3.2 3B in 3 categories; 9 gaps are clear of the uncertainty.
The widest gap is in writing & preference, where Gemma 3 12B leads 47.5 to 24.7.
The biggest single-benchmark swing is Berkeley Function Calling Leaderboard: 30.4% for Gemma 3 12B and 21.9% for Llama 3.2 3B.
Gemma 3 12B is cheaper at $0.05 / $0.15 per million input/output tokens, against $0.05 / $0.33 for Llama 3.2 3B.

Side by side

Gemma 3 12B and Llama 3.2 3B specifications
	Gemma 3 12B	Llama 3.2 3B
Provider	Google	Meta
Noometry Index	32.1	28.9
Released	2025-03-12	2024-09-24
Weights	Open	Open
Context window	131K	131K
Max output	8K	118K
Input $ / M tokens	$0.05	$0.05
Output $ / M tokens	$0.15	$0.33
Results tracked	24	18

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

Category by category

Coding Gemma 3 12B leads

Gemma 3 12B: 31.7 (#280), Llama 3.2 3B: 27.6 (#319)

Coding benchmarks
Benchmark	Gemma 3 12B	Llama 3.2 3B
LMArena Coding	1281	1098
SciCode	17.4%	—
BigCodeBench Instruct	—	23.4%
BigCodeBench Complete	—	28.3%

Agentic & Tool Use Gemma 3 12B leads

Gemma 3 12B: 25.5 (#108), Llama 3.2 3B: 20.1 (#143)

Agentic & Tool Use benchmarks
Benchmark	Gemma 3 12B	Llama 3.2 3B
Berkeley Function Calling Leaderboard	30.4%	21.9%
BALROG	—	10.1%

Reasoning Llama 3.2 3B leads

Gemma 3 12B: 15.7 (#313), Llama 3.2 3B: 21.0 (#228)

Reasoning benchmarks
Benchmark	Gemma 3 12B	Llama 3.2 3B
LMArena Hard Prompts	1309	1095
CritPt	0%	—
Chess Puzzles	0%	—
DTBench	48.8%	—
LMCA	4.5%	—
Epoch Capabilities Index	123.5	—

Math Llama 3.2 3B leads

Gemma 3 12B: 22.3 (#279), Llama 3.2 3B: 32.4 (#214)

Math benchmarks
Benchmark	Gemma 3 12B	Llama 3.2 3B
LMArena Math	1307	1126
OTIS Mock AIME 2024-2025	16.7%	—

Knowledge Llama 3.2 3B leads

Gemma 3 12B: 26.5 (#257), Llama 3.2 3B: 29.7 (#235)

Knowledge benchmarks
Benchmark	Gemma 3 12B	Llama 3.2 3B
LMArena Expert	1248	1090
GPQA Diamond	39.5%	—
Vectara Hallucination Rate	4.4%	—

Multimodal Not comparable

Gemma 3 12B: —, Llama 3.2 3B: —

Multimodal benchmarks
Benchmark	Gemma 3 12B	Llama 3.2 3B
MindCube	46.7%	—

Multilingual Gemma 3 12B leads

Gemma 3 12B: 45.7 (#165), Llama 3.2 3B: 26.2 (#281)

Multilingual benchmarks
Benchmark	Gemma 3 12B	Llama 3.2 3B
LMArena Non-English	1318	1019
LMArena German	1370	1056
LMArena Russian	1335	949
LMArena Chinese	—	1017

Instruction Following Gemma 3 12B leads

Gemma 3 12B: 68.6 (#186), Llama 3.2 3B: 56.0 (#275)

Instruction Following benchmarks
Benchmark	Gemma 3 12B	Llama 3.2 3B
LMArena Instruction Following	1299	1089

Long Context Gemma 3 12B leads

Gemma 3 12B: 40.0 (#162), Llama 3.2 3B: 33.4 (#261)

Long Context benchmarks
Benchmark	Gemma 3 12B	Llama 3.2 3B
LMArena Longer Query	1317	1100

Writing & Preference Gemma 3 12B leads

Gemma 3 12B: 47.5 (#209), Llama 3.2 3B: 24.7 (#307)

Writing & Preference benchmarks
Benchmark	Gemma 3 12B	Llama 3.2 3B
LMArena Text	1334	1110
LMArena Creative Writing	1331	1094
EQ-Bench Creative Writing	1126	595
LMArena Multi-Turn	1334	1105

Frequently asked questions

Is Gemma 3 12B better than Llama 3.2 3B?

Gemma 3 12B is the stronger model overall, scoring 32.1 to 28.9 on the Noometry Index.

Which is cheaper, Gemma 3 12B or Llama 3.2 3B?

Gemma 3 12B is cheaper. It lists at $0.05 per million input tokens and $0.15 per million output tokens; Llama 3.2 3B lists at $0.05 and $0.33.

Is Gemma 3 12B or Llama 3.2 3B better for coding?

Gemma 3 12B scores higher on coding benchmarks: 31.7 versus 27.6 in the Noometry coding category.

Which has the bigger context window?

Both accept 131K tokens.

How many benchmarks do Gemma 3 12B and Llama 3.2 3B share?

14 benchmarks have published results for both models. Gemma 3 12B has 24 scored results on Noometry and Llama 3.2 3B has 18.