Model comparison

Gemma 3 12B vs Qwen3 14B

Qwen3 14B is the stronger model overall, scoring 35.0 to 31.8 on the Noometry Index. Gemma 3 12B costs 8.2× less per token, which makes it the better buy when Qwen3 14B's lead doesn't matter for your workload.

Last verified October 10, 2026. 10 shared benchmarks.

Gemma 3 12B

Google

31.8

Rank #255 Confirmed

Qwen3 14B

Alibaba (Qwen)

35.0

Rank #222 Confirmed

Summary

They share 10 benchmarks with published results for both. Gemma 3 12B scores higher in 1 category and Qwen3 14B in 5 categories; 6 gaps are clear of the uncertainty.
The widest gap is in math, where Qwen3 14B leads 37.0 to 21.0.
The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 16.7% for Gemma 3 12B and 66.4% for Qwen3 14B.
Gemma 3 12B is cheaper at $0.05 / $0.15 per million input/output tokens, against $0.35 / $1.40 for Qwen3 14B.

Side by side

Gemma 3 12B and Qwen3 14B specifications
	Gemma 3 12B	Qwen3 14B
Provider	Google	Alibaba (Qwen)
Noometry Index	31.8	35.0
Released	2025-03-12	2025-04
Weights	Open	Open
Context window	131K	131K
Max output	8K	8K
Input $ / M tokens	$0.05	$0.35
Output $ / M tokens	$0.15	$1.40
Results tracked	24	12

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

Category by category

Coding Qwen3 14B leads

Gemma 3 12B: 31.2 (#276), Qwen3 14B: 36.7 (#191)

Coding benchmarks
Benchmark	Gemma 3 12B	Qwen3 14B
SciCode	17.4%	31.6%
LMArena Coding	1281	—

Agentic & Tool Use Qwen3 14B leads

Gemma 3 12B: 25.3 (#101), Qwen3 14B: 29.4 (#78)

Agentic & Tool Use benchmarks
Benchmark	Gemma 3 12B	Qwen3 14B
Berkeley Function Calling Leaderboard	30.4%	41%

Reasoning Qwen3 14B leads

Gemma 3 12B: 15.2 (#307), Qwen3 14B: 18.1 (#272)

Reasoning benchmarks
Benchmark	Gemma 3 12B	Qwen3 14B
CritPt	0%	0%
Chess Puzzles	0%	4%
DTBench	48.8%	64%
LMCA	4.5%	18.2%
Epoch Capabilities Index	123.49	138.23
Kagi LLM Benchmark	—	49.1%
LMArena Hard Prompts	1309	—

Math Qwen3 14B leads

Gemma 3 12B: 21.0 (#273), Qwen3 14B: 37.0 (#102)

Math benchmarks
Benchmark	Gemma 3 12B	Qwen3 14B
OTIS Mock AIME 2024-2025	16.7%	66.4%
LMArena Math	1307	—

Knowledge Qwen3 14B leads

Gemma 3 12B: 26.5 (#250), Qwen3 14B: 39.2 (#124)

Knowledge benchmarks
Benchmark	Gemma 3 12B	Qwen3 14B
GPQA Diamond	39.5%	63.8%
Vectara Hallucination Rate	4.4%	5.4%
LMArena Expert	1248	—

Multimodal Not comparable

Gemma 3 12B: —, Qwen3 14B: —

Multimodal benchmarks
Benchmark	Gemma 3 12B	Qwen3 14B
MindCube	46.7%	—

Multilingual Not comparable

Gemma 3 12B: 45.9 (#160), Qwen3 14B: —

Multilingual benchmarks
Benchmark	Gemma 3 12B	Qwen3 14B
LMArena Non-English	1318	—
LMArena German	1370	—
LMArena Russian	1335	—

Instruction Following Not comparable

Gemma 3 12B: 68.8 (#179), Qwen3 14B: —

Instruction Following benchmarks
Benchmark	Gemma 3 12B	Qwen3 14B
LMArena Instruction Following	1299	—

Long Context Gemma 3 12B leads

Gemma 3 12B: 40.0 (#157), Qwen3 14B: 38.0 (#201)

Long Context benchmarks
Benchmark	Gemma 3 12B	Qwen3 14B
Fiction.LiveBench	—	62.5%
LMArena Longer Query	1317	—

Writing & Preference Not comparable

Gemma 3 12B: 47.7 (#205), Qwen3 14B: —

Writing & Preference benchmarks
Benchmark	Gemma 3 12B	Qwen3 14B
LMArena Text	1334	—
LMArena Creative Writing	1331	—
EQ-Bench Creative Writing	1126	—
LMArena Multi-Turn	1334	—

Frequently asked questions

Is Gemma 3 12B better than Qwen3 14B?

Which is cheaper, Gemma 3 12B or Qwen3 14B?

Gemma 3 12B is cheaper. It lists at $0.05 per million input tokens and $0.15 per million output tokens; Qwen3 14B lists at $0.35 and $1.40.

Is Gemma 3 12B or Qwen3 14B better for coding?

Qwen3 14B scores higher on coding benchmarks: 36.7 versus 31.2 in the Noometry coding category.

Which has the bigger context window?

Both accept 131K tokens.

How many benchmarks do Gemma 3 12B and Qwen3 14B share?

10 benchmarks have published results for both models. Gemma 3 12B has 24 scored results on Noometry and Qwen3 14B has 12.