Noometry

Model comparison

Gemma 3 4B vs Qwen3-4B

Qwen3-4B is the stronger model overall, scoring 31.9 to 28.1 on the Noometry Index.

Last verified . 5 shared benchmarks.

Gemma 3 4B Google

28.1

Rank #326 Confirmed

Qwen3-4B Alibaba (Qwen)

31.9

Rank #264 Confirmed

Summary

  • They share 5 benchmarks with published results for both. Gemma 3 4B scores higher in 0 categories and Qwen3-4B in 4 categories; 4 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Qwen3-4B leads 33.0 to 11.8.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 7.5% for Gemma 3 4B and 52.2% for Qwen3-4B.

Side by side

Gemma 3 4BQwen3-4B
ProviderGoogleAlibaba (Qwen)
Noometry Index28.131.9
Released2025-03-122025-04-29
WeightsOpenOpen
Context window131K—
Max output4K—
Input $ / M tokens$0.04—
Output $ / M tokens$0.08—
Results tracked226

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

Category by category

Coding Not comparable

Gemma 3 4B: 35.9 (#215), Qwen3-4B: —

BenchmarkGemma 3 4BQwen3-4B
LMArena Coding1230—

Agentic & Tool Use Qwen3-4B leads

Gemma 3 4B: 20.9 (#142), Qwen3-4B: 27.6 (#100)

BenchmarkGemma 3 4BQwen3-4B
Berkeley Function Calling Leaderboard19.6%35.7%

Reasoning Qwen3-4B leads

Gemma 3 4B: 13.2 (#335), Qwen3-4B: 19.2 (#268)

BenchmarkGemma 3 4BQwen3-4B
Chess Puzzles0%4%
Kagi LLM Benchmark25.2%—
LMArena Hard Prompts1253—
DTBench50.9%—
LMCA2.8%—
Epoch Capabilities Index116.02—

Math Qwen3-4B leads

Gemma 3 4B: 16.8 (#292), Qwen3-4B: 29.7 (#240)

BenchmarkGemma 3 4BQwen3-4B
OTIS Mock AIME 2024-20257.5%52.2%
MathArena Final-Answer Competitions—38.5%
LMArena Math1239—

Knowledge Qwen3-4B leads

Gemma 3 4B: 11.8 (#299), Qwen3-4B: 33.0 (#208)

BenchmarkGemma 3 4BQwen3-4B
GPQA Diamond23.2%52.3%
Vectara Hallucination Rate6.4%5.7%
LMArena Expert1223—

Multilingual Not comparable

Gemma 3 4B: 42.5 (#194), Qwen3-4B: —

BenchmarkGemma 3 4BQwen3-4B
LMArena Non-English1273—
LMArena German1281—
LMArena Russian1294—

Instruction Following Not comparable

Gemma 3 4B: 65.2 (#225), Qwen3-4B: —

BenchmarkGemma 3 4BQwen3-4B
LMArena Instruction Following1239—

Long Context Not comparable

Gemma 3 4B: 38.7 (#194), Qwen3-4B: —

BenchmarkGemma 3 4BQwen3-4B
LMArena Longer Query1273—

Writing & Preference Not comparable

Gemma 3 4B: 42.0 (#239), Qwen3-4B: —

BenchmarkGemma 3 4BQwen3-4B
LMArena Text1291—
LMArena Creative Writing1271—
EQ-Bench Creative Writing1068—
LMArena Multi-Turn1255—

Frequently asked questions

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

Qwen3-4B is the stronger model overall, scoring 31.9 to 28.1 on the Noometry Index.

How many benchmarks do Gemma 3 4B and Qwen3-4B share?

5 benchmarks have published results for both models. Gemma 3 4B has 22 scored results on Noometry and Qwen3-4B has 6.

Related comparisons

Go deeper