Model comparison

Gemma 3 12B vs Qwen2.5 14B Instruct

Gemma 3 12B has enough public results to be ranked (#255); Qwen2.5 14B Instruct does not yet, so treat this comparison as directional.

Last verified October 10, 2026. 0 shared benchmarks.

Gemma 3 12B

Google

31.8

Rank #255 Confirmed

Qwen2.5 14B Instruct

Alibaba (Qwen)

38.2

Unranked Sparse

Summary

The widest gap is in coding, where Qwen2.5 14B Instruct leads 37.1 to 31.2.
Gemma 3 12B is cheaper at $0.05 / $0.15 per million input/output tokens, against $0.35 / $1.40 for Qwen2.5 14B Instruct.

Side by side

Gemma 3 12B and Qwen2.5 14B Instruct specifications
	Gemma 3 12B	Qwen2.5 14B Instruct
Provider	Google	Alibaba (Qwen)
Noometry Index	31.8	38.2
Released	2025-03-12	2024-09
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	3

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

Category by category

Coding Qwen2.5 14B Instruct leads

Gemma 3 12B: 31.2 (#276), Qwen2.5 14B Instruct: 37.1 (#187)

Coding benchmarks
Benchmark	Gemma 3 12B	Qwen2.5 14B Instruct
SciCode	17.4%	—
BigCodeBench Instruct	—	39.8%
LMArena Coding	1281	—
BigCodeBench Complete	—	52.2%

Agentic & Tool Use Not comparable

Gemma 3 12B: 25.3 (#101), Qwen2.5 14B Instruct: —

Agentic & Tool Use benchmarks
Benchmark	Gemma 3 12B	Qwen2.5 14B Instruct
Berkeley Function Calling Leaderboard	30.4%	—

Reasoning Not comparable

Gemma 3 12B: 15.2 (#307), Qwen2.5 14B Instruct: —

Reasoning benchmarks
Benchmark	Gemma 3 12B	Qwen2.5 14B Instruct
CritPt	0%	—
Chess Puzzles	0%	—
LMArena Hard Prompts	1309	—
DTBench	48.8%	—
LMCA	4.5%	—
Epoch Capabilities Index	123.49	—

Math Not comparable

Gemma 3 12B: 21.0 (#273), Qwen2.5 14B Instruct: —

Math benchmarks
Benchmark	Gemma 3 12B	Qwen2.5 14B Instruct
OTIS Mock AIME 2024-2025	16.7%	—
LMArena Math	1307	—

Knowledge Not comparable

Gemma 3 12B: 26.5 (#250), Qwen2.5 14B Instruct: —

Knowledge benchmarks
Benchmark	Gemma 3 12B	Qwen2.5 14B Instruct
GPQA Diamond	39.5%	—
Vectara Hallucination Rate	4.4%	—
LMArena Expert	1248	—
MMLU	—	79.9%

Multimodal Not comparable

Gemma 3 12B: —, Qwen2.5 14B Instruct: —

Multimodal benchmarks
Benchmark	Gemma 3 12B	Qwen2.5 14B Instruct
MindCube	46.7%	—

Multilingual Not comparable

Gemma 3 12B: 45.9 (#160), Qwen2.5 14B Instruct: —

Multilingual benchmarks
Benchmark	Gemma 3 12B	Qwen2.5 14B Instruct
LMArena Non-English	1318	—
LMArena German	1370	—
LMArena Russian	1335	—

Instruction Following Not comparable

Gemma 3 12B: 68.8 (#179), Qwen2.5 14B Instruct: —

Instruction Following benchmarks
Benchmark	Gemma 3 12B	Qwen2.5 14B Instruct
LMArena Instruction Following	1299	—

Long Context Not comparable

Gemma 3 12B: 40.0 (#157), Qwen2.5 14B Instruct: —

Long Context benchmarks
Benchmark	Gemma 3 12B	Qwen2.5 14B Instruct
LMArena Longer Query	1317	—

Writing & Preference Not comparable

Gemma 3 12B: 47.7 (#205), Qwen2.5 14B Instruct: —

Writing & Preference benchmarks
Benchmark	Gemma 3 12B	Qwen2.5 14B Instruct
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 Qwen2.5 14B Instruct?

Gemma 3 12B has enough public results to be ranked (#255); Qwen2.5 14B Instruct does not yet, so treat this comparison as directional.

Which is cheaper, Gemma 3 12B or Qwen2.5 14B Instruct?

Gemma 3 12B is cheaper. It lists at $0.05 per million input tokens and $0.15 per million output tokens; Qwen2.5 14B Instruct lists at $0.35 and $1.40.

Is Gemma 3 12B or Qwen2.5 14B Instruct better for coding?

Qwen2.5 14B Instruct scores higher on coding benchmarks: 37.1 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 Qwen2.5 14B Instruct share?

0 benchmarks have published results for both models. Gemma 3 12B has 24 scored results on Noometry and Qwen2.5 14B Instruct has 3.