Model comparison

Gemma 3 4B vs Qwen3-1.7B

Gemma 3 4B is the stronger model overall, scoring 28.1 to 26.6 on the Noometry Index.

Last verified October 10, 2026. 4 shared benchmarks.

Gemma 3 4B

Google

28.1

Rank #326 Confirmed

Qwen3-1.7B

Alibaba (Qwen)

26.6

Rank #336 Reported

Summary

They share 4 benchmarks with published results for both. Gemma 3 4B scores higher in 1 category and Qwen3-1.7B in 3 categories; 3 gaps are clear of the uncertainty.
The widest gap is in knowledge, where Qwen3-1.7B leads 19.6 to 11.8.
The biggest single-benchmark swing is GPQA Diamond: 23.2% for Gemma 3 4B and 38% for Qwen3-1.7B.

Side by side

Gemma 3 4B and Qwen3-1.7B specifications
	Gemma 3 4B	Qwen3-1.7B
Provider	Google	Alibaba (Qwen)
Noometry Index	28.1	26.6
Released	2025-03-12	2025-04-29
Weights	Open	Open
Context window	131K	—
Max output	4K	—
Input $ / M tokens	$0.04	—
Output $ / M tokens	$0.08	—
Results tracked	22	4

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

Category by category

Coding Not comparable

Gemma 3 4B: 35.9 (#215), Qwen3-1.7B: —

Coding benchmarks
Benchmark	Gemma 3 4B	Qwen3-1.7B
LMArena Coding	1230	—

Agentic & Tool Use Qwen3-1.7B leads

Gemma 3 4B: 20.9 (#142), Qwen3-1.7B: 24.7 (#115)

Agentic & Tool Use benchmarks
Benchmark	Gemma 3 4B	Qwen3-1.7B
Berkeley Function Calling Leaderboard	19.6%	28.4%

Reasoning Qwen3-1.7B leads

Gemma 3 4B: 13.2 (#335), Qwen3-1.7B: 19.2 (#267)

Reasoning benchmarks
Benchmark	Gemma 3 4B	Qwen3-1.7B
Chess Puzzles	0%	0%
Kagi LLM Benchmark	25.2%	—
LMArena Hard Prompts	1253	—
DTBench	50.9%	—
LMCA	2.8%	—
Epoch Capabilities Index	116.02	—

Math Too close to call

Gemma 3 4B: 16.8 (#292), Qwen3-1.7B: 16.3 (#294)

Math benchmarks
Benchmark	Gemma 3 4B	Qwen3-1.7B
OTIS Mock AIME 2024-2025	7.5%	8.1%
LMArena Math	1239	—

Knowledge Qwen3-1.7B leads

Gemma 3 4B: 11.8 (#299), Qwen3-1.7B: 19.6 (#278)

Knowledge benchmarks
Benchmark	Gemma 3 4B	Qwen3-1.7B
GPQA Diamond	23.2%	38%
Vectara Hallucination Rate	6.4%	—
LMArena Expert	1223	—

Multilingual Not comparable

Gemma 3 4B: 42.5 (#194), Qwen3-1.7B: —

Multilingual benchmarks
Benchmark	Gemma 3 4B	Qwen3-1.7B
LMArena Non-English	1273	—
LMArena German	1281	—
LMArena Russian	1294	—

Instruction Following Not comparable

Gemma 3 4B: 65.2 (#225), Qwen3-1.7B: —

Instruction Following benchmarks
Benchmark	Gemma 3 4B	Qwen3-1.7B
LMArena Instruction Following	1239	—

Long Context Not comparable

Gemma 3 4B: 38.7 (#194), Qwen3-1.7B: —

Long Context benchmarks
Benchmark	Gemma 3 4B	Qwen3-1.7B
LMArena Longer Query	1273	—

Writing & Preference Not comparable

Gemma 3 4B: 42.0 (#239), Qwen3-1.7B: —

Writing & Preference benchmarks
Benchmark	Gemma 3 4B	Qwen3-1.7B
LMArena Text	1291	—
LMArena Creative Writing	1271	—
EQ-Bench Creative Writing	1068	—
LMArena Multi-Turn	1255	—

Frequently asked questions

Is Gemma 3 4B better than Qwen3-1.7B?