Noometry

Model comparison

Gemma 3 27B vs Qwen1.5-32B

Gemma 3 27B and Qwen1.5-32B score almost the same on the Noometry Index (30.5 vs 30.0), so choose on price, context window or the category you care about most.

Last verified . 18 shared benchmarks.

Gemma 3 27B Google

30.5

Rank #277 Confirmed

Qwen1.5-32B Alibaba (Qwen)

30.0

Rank #288 Confirmed

Summary

  • They share 18 benchmarks with published results for both. Gemma 3 27B scores higher in 4 categories and Qwen1.5-32B in 4 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in writing & preference, where Gemma 3 27B leads 52.7 to 34.4.
  • The biggest single-benchmark swing is GPQA Diamond: 47.7% for Gemma 3 27B and 30.7% for Qwen1.5-32B.

Side by side

Gemma 3 27BQwen1.5-32B
ProviderGoogleAlibaba (Qwen)
Noometry Index30.530.0
Released2025-03-112024-02-04
WeightsOpenOpen
Context window131K—
Max output8K—
Input $ / M tokens$0.08—
Output $ / M tokens$0.16—
Results tracked4321

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

Category by category

Coding Qwen1.5-32B leads

Gemma 3 27B: 22.1 (#329), Qwen1.5-32B: 31.1 (#278)

BenchmarkGemma 3 27BQwen1.5-32B
LMArena Coding13221155
Aider Polyglot4.9%—
SciCode21.2%—
BigCodeBench Instruct—32.3%
LiveBench Coding39.9%—
BigCodeBench Complete—42%

Agentic & Tool Use Not comparable

Gemma 3 27B: 24.9 (#105), Qwen1.5-32B: —

BenchmarkGemma 3 27BQwen1.5-32B
Berkeley Function Calling Leaderboard29.5%—

Reasoning Qwen1.5-32B leads

Gemma 3 27B: 16.3 (#297), Qwen1.5-32B: 20.9 (#210)

BenchmarkGemma 3 27BQwen1.5-32B
LMArena Hard Prompts13401131
Kagi LLM Benchmark40.4%—
CritPt0%—
Chess Puzzles0%—
LiveBench Reasoning43.8%—
DTBench52.5%—
LiveBench Data Analysis51.5%—
LMCA12.3%—
Epoch Capabilities Index130.04—
LiveBench50%—

Math Qwen1.5-32B leads

Gemma 3 27B: 24.4 (#261), Qwen1.5-32B: 30.5 (#207)

BenchmarkGemma 3 27BQwen1.5-32B
LMArena Math13121155
OTIS Mock AIME 2024-202522.5%—
LiveBench Math55.4%—
MATH Level 574%—

Knowledge Gemma 3 27B leads

Gemma 3 27B: 25.4 (#256), Qwen1.5-32B: 13.5 (#291)

BenchmarkGemma 3 27BQwen1.5-32B
GPQA Diamond47.7%30.7%
LMArena Expert13031126
Confabulations40.3%—
Vectara Hallucination Rate7.4%—
MMLU—74.4%

Multimodal Not comparable

Gemma 3 27B: 32.0 (#94), Qwen1.5-32B: —

BenchmarkGemma 3 27BQwen1.5-32B
LMArena Vision1165—
GeoBench52%—

Multilingual Gemma 3 27B leads

Gemma 3 27B: 47.0 (#150), Qwen1.5-32B: 31.6 (#254)

BenchmarkGemma 3 27BQwen1.5-32B
LMArena Non-English13341106
LMArena Chinese13471176
LMArena French13681100
LMArena German13621058
LMArena Japanese12871027
LMArena Korean13081007
LMArena Russian13491073
LMArena Spanish13481089

Instruction Following Gemma 3 27B leads

Gemma 3 27B: 70.8 (#155), Qwen1.5-32B: 58.0 (#260)

BenchmarkGemma 3 27BQwen1.5-32B
LMArena Instruction Following13211116
LiveBench Instruction Following74.9%—

Long Context Qwen1.5-32B leads

Gemma 3 27B: 27.6 (#288), Qwen1.5-32B: 34.7 (#241)

BenchmarkGemma 3 27BQwen1.5-32B
LMArena Longer Query13331146
Fiction.LiveBench33.3%—

Writing & Preference Gemma 3 27B leads

Gemma 3 27B: 52.7 (#161), Qwen1.5-32B: 34.4 (#266)

BenchmarkGemma 3 27BQwen1.5-32B
LMArena Text13581137
LMArena Creative Writing13461083
LMArena Multi-Turn13441140
Short-Story Creative Writing79.9%—
EQ-Bench Creative Writing1266—
LiveBench Language34.6%—

Frequently asked questions

Is Gemma 3 27B better than Qwen1.5-32B?

Gemma 3 27B and Qwen1.5-32B score almost the same on the Noometry Index (30.5 vs 30.0), so choose on price, context window or the category you care about most.

Is Gemma 3 27B or Qwen1.5-32B better for coding?

Qwen1.5-32B scores higher on coding benchmarks: 31.1 versus 22.1 in the Noometry coding category.

How many benchmarks do Gemma 3 27B and Qwen1.5-32B share?

18 benchmarks have published results for both models. Gemma 3 27B has 43 scored results on Noometry and Qwen1.5-32B has 21.

Related comparisons

Go deeper