Model comparison

Gemma 3 12B vs Qwen3 32B

Qwen3 32B is the stronger model overall, scoring 39.2 to 32.1 on the Noometry Index. Gemma 3 12B costs 16× less per token, which makes it the better buy when Qwen3 32B's lead doesn't matter for your workload.

Last verified October 11, 2026. 22 shared benchmarks.

Gemma 3 12B

Google

32.1

Rank #262 Confirmed

Qwen3 32B

Alibaba (Qwen)

39.2

Rank #172 Confirmed

Summary

They share 22 benchmarks with published results for both. Gemma 3 12B scores higher in 1 category and Qwen3 32B in 8 categories; 7 gaps are clear of the uncertainty.
The widest gap is in math, where Qwen3 32B leads 39.7 to 22.3.
The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 16.7% for Gemma 3 12B and 66.9% for Qwen3 32B.
Gemma 3 12B is cheaper at $0.05 / $0.15 per million input/output tokens, against $0.70 / $2.80 for Qwen3 32B.

Side by side

Gemma 3 12B and Qwen3 32B specifications
	Gemma 3 12B	Qwen3 32B
Provider	Google	Alibaba (Qwen)
Noometry Index	32.1	39.2
Released	2025-03-12	2025-04
Weights	Open	Open
Context window	131K	131K
Max output	8K	16K
Input $ / M tokens	$0.05	$0.70
Output $ / M tokens	$0.15	$2.80
Results tracked	24	26

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

Category by category

Coding Qwen3 32B leads

Gemma 3 12B: 31.7 (#280), Qwen3 32B: 37.7 (#190)

Coding benchmarks
Benchmark	Gemma 3 12B	Qwen3 32B
SciCode	17.4%	35.4%
LMArena Coding	1281	1358
Aider Polyglot	—	40%

Agentic & Tool Use Qwen3 32B leads

Gemma 3 12B: 25.5 (#108), Qwen3 32B: 32.6 (#62)

Agentic & Tool Use benchmarks
Benchmark	Gemma 3 12B	Qwen3 32B
Berkeley Function Calling Leaderboard	30.4%	48.7%

Reasoning Qwen3 32B leads

Gemma 3 12B: 15.7 (#313), Qwen3 32B: 20.2 (#241)

Reasoning benchmarks
Benchmark	Gemma 3 12B	Qwen3 32B
CritPt	0%	0.3%
Chess Puzzles	0%	5%
LMArena Hard Prompts	1309	1334
DTBench	48.8%	67.5%
LMCA	4.5%	17.3%
Epoch Capabilities Index	123.5	138.51
Kagi LLM Benchmark	—	54.9%

Math Qwen3 32B leads

Gemma 3 12B: 22.3 (#279), Qwen3 32B: 39.7 (#99)

Math benchmarks
Benchmark	Gemma 3 12B	Qwen3 32B
OTIS Mock AIME 2024-2025	16.7%	66.9%
LMArena Math	1307	1399

Knowledge Qwen3 32B leads

Gemma 3 12B: 26.5 (#257), Qwen3 32B: 40.0 (#125)

Knowledge benchmarks
Benchmark	Gemma 3 12B	Qwen3 32B
GPQA Diamond	39.5%	65.7%
Vectara Hallucination Rate	4.4%	5.9%
LMArena Expert	1248	1362

Multimodal Not comparable

Gemma 3 12B: —, Qwen3 32B: —

Multimodal benchmarks
Benchmark	Gemma 3 12B	Qwen3 32B
MindCube	46.7%	—

Multilingual Too close to call

Gemma 3 12B: 45.7 (#165), Qwen3 32B: 45.6 (#167)

Multilingual benchmarks
Benchmark	Gemma 3 12B	Qwen3 32B
LMArena Non-English	1318	1317
LMArena German	1370	1341
LMArena Russian	1335	1311
LMArena Chinese	—	1357

Instruction Following Too close to call

Gemma 3 12B: 68.6 (#186), Qwen3 32B: 68.9 (#179)

Instruction Following benchmarks
Benchmark	Gemma 3 12B	Qwen3 32B
LMArena Instruction Following	1299	1305

Long Context Qwen3 32B leads

Gemma 3 12B: 40.0 (#162), Qwen3 32B: 43.8 (#87)

Long Context benchmarks
Benchmark	Gemma 3 12B	Qwen3 32B
LMArena Longer Query	1317	1327
Fiction.LiveBench	—	74.2%

Writing & Preference Qwen3 32B leads

Gemma 3 12B: 47.5 (#209), Qwen3 32B: 52.9 (#163)

Writing & Preference benchmarks
Benchmark	Gemma 3 12B	Qwen3 32B
LMArena Text	1334	1340
LMArena Creative Writing	1331	1297
LMArena Multi-Turn	1334	1331
EQ-Bench Creative Writing	1126	—

Frequently asked questions

Is Gemma 3 12B better than Qwen3 32B?

Which is cheaper, Gemma 3 12B or Qwen3 32B?

Gemma 3 12B is cheaper. It lists at $0.05 per million input tokens and $0.15 per million output tokens; Qwen3 32B lists at $0.70 and $2.80.

Is Gemma 3 12B or Qwen3 32B better for coding?

Qwen3 32B scores higher on coding benchmarks: 37.7 versus 31.7 in the Noometry coding category.

Which has the bigger context window?

Both accept 131K tokens.

How many benchmarks do Gemma 3 12B and Qwen3 32B share?

22 benchmarks have published results for both models. Gemma 3 12B has 24 scored results on Noometry and Qwen3 32B has 26.