Model comparison

Gemma 3 12B vs Llama 3.2 1B

Gemma 3 12B is the stronger model overall, scoring 31.8 to 19.9 on the Noometry Index.

Last verified October 10, 2026. 18 shared benchmarks.

Gemma 3 12B

Google

31.8

Rank #255 Confirmed

Llama 3.2 1B

Summary

They share 18 benchmarks with published results for both. Gemma 3 12B scores higher in 8 categories and Llama 3.2 1B in 1 category; 8 gaps are clear of the uncertainty.
The widest gap is in writing & preference, where Gemma 3 12B leads 47.7 to 21.4.
The biggest single-benchmark swing is Berkeley Function Calling Leaderboard: 30.4% for Gemma 3 12B and 10.8% for Llama 3.2 1B.
Llama 3.2 1B is cheaper at $0.027 / $0.20 per million input/output tokens, against $0.05 / $0.15 for Gemma 3 12B.
Gemma 3 12B accepts more context: 131K tokens versus 60K.

Side by side

Gemma 3 12B and Llama 3.2 1B specifications
	Gemma 3 12B	Llama 3.2 1B
Provider	Google	Meta
Noometry Index	31.8	19.9
Released	2025-03-12	2024-09-24
Weights	Open	Open
Context window	131K	60K
Max output	8K	54K
Input $ / M tokens	$0.05	$0.027
Output $ / M tokens	$0.15	$0.20
Results tracked	24	22

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

Category by category

Coding Gemma 3 12B leads

Gemma 3 12B: 31.2 (#276), Llama 3.2 1B: 20.6 (#333)

Coding benchmarks
Benchmark	Gemma 3 12B	Llama 3.2 1B
LMArena Coding	1281	1071
SciCode	17.4%	—
BigCodeBench Instruct	—	8.2%
BigCodeBench Complete	—	11.3%

Agentic & Tool Use Gemma 3 12B leads

Gemma 3 12B: 25.3 (#101), Llama 3.2 1B: 14.5 (#142)

Agentic & Tool Use benchmarks
Benchmark	Gemma 3 12B	Llama 3.2 1B
Berkeley Function Calling Leaderboard	30.4%	10.8%
BALROG	—	6.6%

Reasoning Too close to call

Gemma 3 12B: 15.2 (#307), Llama 3.2 1B: 15.6 (#304)

Reasoning benchmarks
Benchmark	Gemma 3 12B	Llama 3.2 1B
Chess Puzzles	0%	0%
LMArena Hard Prompts	1309	1044
Epoch Capabilities Index	123.49	101.95
CritPt	0%	—
DTBench	48.8%	—
LMCA	4.5%	—

Math Gemma 3 12B leads

Gemma 3 12B: 21.0 (#273), Llama 3.2 1B: 9.7 (#308)

Math benchmarks
Benchmark	Gemma 3 12B	Llama 3.2 1B
OTIS Mock AIME 2024-2025	16.7%	0.6%
LMArena Math	1307	1086

Knowledge Gemma 3 12B leads

Gemma 3 12B: 26.5 (#250), Llama 3.2 1B: 7.2 (#307)

Knowledge benchmarks
Benchmark	Gemma 3 12B	Llama 3.2 1B
GPQA Diamond	39.5%	23.9%
LMArena Expert	1248	1007
Vectara Hallucination Rate	4.4%	—

Multimodal Not comparable

Gemma 3 12B: —, Llama 3.2 1B: —

Multimodal benchmarks
Benchmark	Gemma 3 12B	Llama 3.2 1B
MindCube	46.7%	—

Multilingual Gemma 3 12B leads

Gemma 3 12B: 45.9 (#160), Llama 3.2 1B: 23.9 (#287)

Multilingual benchmarks
Benchmark	Gemma 3 12B	Llama 3.2 1B
LMArena Non-English	1318	973
LMArena German	1370	1014
LMArena Russian	1335	941
LMArena Chinese	—	958

Instruction Following Gemma 3 12B leads

Gemma 3 12B: 68.8 (#179), Llama 3.2 1B: 52.6 (#285)

Instruction Following benchmarks
Benchmark	Gemma 3 12B	Llama 3.2 1B
LMArena Instruction Following	1299	1031

Long Context Gemma 3 12B leads

Gemma 3 12B: 40.0 (#157), Llama 3.2 1B: 31.9 (#269)

Long Context benchmarks
Benchmark	Gemma 3 12B	Llama 3.2 1B
LMArena Longer Query	1317	1050

Writing & Preference Gemma 3 12B leads

Gemma 3 12B: 47.7 (#205), Llama 3.2 1B: 21.4 (#305)

Writing & Preference benchmarks
Benchmark	Gemma 3 12B	Llama 3.2 1B
LMArena Text	1334	1055
LMArena Creative Writing	1331	1033
EQ-Bench Creative Writing	1126	200
LMArena Multi-Turn	1334	1030

Frequently asked questions

Is Gemma 3 12B better than Llama 3.2 1B?

Gemma 3 12B is the stronger model overall, scoring 31.8 to 19.9 on the Noometry Index.

Which is cheaper, Gemma 3 12B or Llama 3.2 1B?

Llama 3.2 1B is cheaper. It lists at $0.027 per million input tokens and $0.20 per million output tokens; Gemma 3 12B lists at $0.05 and $0.15.

Is Gemma 3 12B or Llama 3.2 1B better for coding?

Gemma 3 12B scores higher on coding benchmarks: 31.2 versus 20.6 in the Noometry coding category.

Which has the bigger context window?

Gemma 3 12B does, with 131K tokens against 60K.

How many benchmarks do Gemma 3 12B and Llama 3.2 1B share?

18 benchmarks have published results for both models. Gemma 3 12B has 24 scored results on Noometry and Llama 3.2 1B has 22.