Model comparison

Gemma 3 12B vs Qwen3.5-9B

Qwen3.5-9B is the stronger model overall, scoring 33.3 to 31.8 on the Noometry Index. Gemma 3 12B costs 1.5× less per token, which makes it the better buy when Qwen3.5-9B's lead doesn't matter for your workload.

Last verified October 10, 2026. 8 shared benchmarks.

Gemma 3 12B

Google

31.8

Rank #255 Confirmed

Qwen3.5-9B

Alibaba (Qwen)

33.3

Rank #235 Confirmed

Summary

They share 8 benchmarks with published results for both. Gemma 3 12B scores higher in 1 category and Qwen3.5-9B in 4 categories; 5 gaps are clear of the uncertainty.
The widest gap is in knowledge, where Qwen3.5-9B leads 46.0 to 26.5.
The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 16.7% for Gemma 3 12B and 61.7% for Qwen3.5-9B.
Gemma 3 12B is cheaper at $0.05 / $0.15 per million input/output tokens, against $0.10 / $0.15 for Qwen3.5-9B.
Qwen3.5-9B accepts more context: 262K tokens versus 131K.

Side by side

Gemma 3 12B and Qwen3.5-9B specifications
	Gemma 3 12B	Qwen3.5-9B
Provider	Google	Alibaba (Qwen)
Noometry Index	31.8	33.3
Released	2025-03-12	2026-02-23
Weights	Open	Open
Context window	131K	262K
Max output	8K	66K
Input $ / M tokens	$0.05	$0.10
Output $ / M tokens	$0.15	$0.15
Results tracked	24	10

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

Category by category

Coding Qwen3.5-9B leads

Gemma 3 12B: 31.2 (#276), Qwen3.5-9B: 35.3 (#213)

Coding benchmarks
Benchmark	Gemma 3 12B	Qwen3.5-9B
SciCode	17.4%	27.5%
LMArena Coding	1281	—

Agentic & Tool Use Gemma 3 12B leads

Gemma 3 12B: 25.3 (#101), Qwen3.5-9B: 14.4 (#143)

Agentic & Tool Use benchmarks
Benchmark	Gemma 3 12B	Qwen3.5-9B
Terminal-Bench	—	9.2%
Berkeley Function Calling Leaderboard	30.4%	—

Reasoning Qwen3.5-9B leads

Gemma 3 12B: 15.2 (#307), Qwen3.5-9B: 22.5 (#178)

Reasoning benchmarks
Benchmark	Gemma 3 12B	Qwen3.5-9B
CritPt	0%	0.3%
Chess Puzzles	0%	12%
DTBench	48.8%	71.2%
LMCA	4.5%	24.5%
Epoch Capabilities Index	123.49	139.45
LMArena Hard Prompts	1309	—

Math Qwen3.5-9B leads

Gemma 3 12B: 21.0 (#273), Qwen3.5-9B: 33.5 (#174)

Math benchmarks
Benchmark	Gemma 3 12B	Qwen3.5-9B
OTIS Mock AIME 2024-2025	16.7%	61.7%
MathArena Final-Answer Competitions	—	48.5%
LMArena Math	1307	—

Knowledge Qwen3.5-9B leads

Gemma 3 12B: 26.5 (#250), Qwen3.5-9B: 46.0 (#77)

Knowledge benchmarks
Benchmark	Gemma 3 12B	Qwen3.5-9B
GPQA Diamond	39.5%	79%
Vectara Hallucination Rate	4.4%	—
LMArena Expert	1248	—

Multimodal Not comparable

Gemma 3 12B: —, Qwen3.5-9B: —

Multimodal benchmarks
Benchmark	Gemma 3 12B	Qwen3.5-9B
MindCube	46.7%	—

Multilingual Not comparable

Gemma 3 12B: 45.9 (#160), Qwen3.5-9B: —

Multilingual benchmarks
Benchmark	Gemma 3 12B	Qwen3.5-9B
LMArena Non-English	1318	—
LMArena German	1370	—
LMArena Russian	1335	—

Instruction Following Not comparable

Gemma 3 12B: 68.8 (#179), Qwen3.5-9B: —

Instruction Following benchmarks
Benchmark	Gemma 3 12B	Qwen3.5-9B
LMArena Instruction Following	1299	—

Long Context Not comparable

Gemma 3 12B: 40.0 (#157), Qwen3.5-9B: —

Long Context benchmarks
Benchmark	Gemma 3 12B	Qwen3.5-9B
LMArena Longer Query	1317	—

Writing & Preference Not comparable

Gemma 3 12B: 47.7 (#205), Qwen3.5-9B: —

Writing & Preference benchmarks
Benchmark	Gemma 3 12B	Qwen3.5-9B
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 Qwen3.5-9B?

Which is cheaper, Gemma 3 12B or Qwen3.5-9B?

Gemma 3 12B is cheaper. It lists at $0.05 per million input tokens and $0.15 per million output tokens; Qwen3.5-9B lists at $0.10 and $0.15.

Is Gemma 3 12B or Qwen3.5-9B better for coding?

Qwen3.5-9B scores higher on coding benchmarks: 35.3 versus 31.2 in the Noometry coding category.

Which has the bigger context window?

Qwen3.5-9B does, with 262K tokens against 131K.

How many benchmarks do Gemma 3 12B and Qwen3.5-9B share?

8 benchmarks have published results for both models. Gemma 3 12B has 24 scored results on Noometry and Qwen3.5-9B has 10.