Noometry

Model comparison

Gemma 3 27B vs Qwen2.5-Max

Qwen2.5-Max is the stronger model overall, scoring 40.7 to 30.8 on the Noometry Index.

Last verified . 27 shared benchmarks.

Gemma 3 27B Google

30.8

Rank #284 Confirmed

Qwen2.5-Max Alibaba (Qwen)

40.7

Rank #146 Confirmed

Summary

  • They share 27 benchmarks with published results for both. Gemma 3 27B scores higher in 0 categories and Qwen2.5-Max in 8 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in coding, where Qwen2.5-Max leads 41.8 to 22.5.
  • The biggest single-benchmark swing is LiveBench Coding: 39.9% for Gemma 3 27B and 64.4% for Qwen2.5-Max.
  • Gemma 3 27B has downloadable open weights; the other is API-only.

Side by side

Gemma 3 27BQwen2.5-Max
ProviderGoogleAlibaba (Qwen)
Noometry Index30.840.7
Released2025-03-112025-01-25
WeightsOpenProprietary
Context window131K—
Max output8K—
Input $ / M tokens$0.08—
Output $ / M tokens$0.16—
Results tracked4327

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

Category by category

Coding Qwen2.5-Max leads

Gemma 3 27B: 22.5 (#334), Qwen2.5-Max: 41.8 (#117)

BenchmarkGemma 3 27BQwen2.5-Max
LiveBench Coding39.9%64.4%
LMArena Coding13221359
Aider Polyglot4.9%—
SciCode21.2%—

Agentic & Tool Use Not comparable

Gemma 3 27B: 25.1 (#110), Qwen2.5-Max: —

BenchmarkGemma 3 27BQwen2.5-Max
Berkeley Function Calling Leaderboard29.5%—

Reasoning Qwen2.5-Max leads

Gemma 3 27B: 16.7 (#301), Qwen2.5-Max: 25.6 (#147)

BenchmarkGemma 3 27BQwen2.5-Max
LiveBench Reasoning43.8%51.4%
LMArena Hard Prompts13401360
LiveBench Data Analysis51.5%67.9%
Epoch Capabilities Index130.04132.53
LiveBench50%62.3%
Kagi LLM Benchmark40.4%—
CritPt0%—
Chess Puzzles0%—
DTBench52.5%—
LMCA12.3%—

Math Qwen2.5-Max leads

Gemma 3 27B: 25.9 (#265), Qwen2.5-Max: 36.9 (#162)

BenchmarkGemma 3 27BQwen2.5-Max
LiveBench Math55.4%58.4%
LMArena Math13121369
OTIS Mock AIME 2024-202522.5%—
MATH Level 574%—

Knowledge Qwen2.5-Max leads

Gemma 3 27B: 25.5 (#261), Qwen2.5-Max: 35.3 (#186)

BenchmarkGemma 3 27BQwen2.5-Max
Confabulations40.3%21.8%
LMArena Expert13041337
GPQA Diamond47.7%—
Vectara Hallucination Rate7.4%—

Multimodal Not comparable

Gemma 3 27B: 32.6 (#100), Qwen2.5-Max: —

BenchmarkGemma 3 27BQwen2.5-Max
LMArena Vision1164—
GeoBench52%—

Multilingual Qwen2.5-Max leads

Gemma 3 27B: 46.9 (#155), Qwen2.5-Max: 48.1 (#146)

BenchmarkGemma 3 27BQwen2.5-Max
LMArena Non-English13341352
LMArena Chinese13461382
LMArena French13681396
LMArena German13621350
LMArena Japanese12871300
LMArena Korean13081304
LMArena Russian13491353
LMArena Spanish13491377

Instruction Following Too close to call

Gemma 3 27B: 70.6 (#160), Qwen2.5-Max: 71.3 (#152)

BenchmarkGemma 3 27BQwen2.5-Max
LiveBench Instruction Following74.9%75.3%
LMArena Instruction Following13211335

Long Context Qwen2.5-Max leads

Gemma 3 27B: 27.6 (#293), Qwen2.5-Max: 41.4 (#142)

BenchmarkGemma 3 27BQwen2.5-Max
LMArena Longer Query13331358
Fiction.LiveBench33.3%—

Writing & Preference Qwen2.5-Max leads

Gemma 3 27B: 52.5 (#168), Qwen2.5-Max: 55.4 (#146)

BenchmarkGemma 3 27BQwen2.5-Max
LMArena Text13581367
LMArena Creative Writing13461339
Short-Story Creative Writing79.9%72.9%
LMArena Multi-Turn13451364
LiveBench Language34.6%56.3%
EQ-Bench Creative Writing1266—

Frequently asked questions

Is Gemma 3 27B better than Qwen2.5-Max?

Qwen2.5-Max is the stronger model overall, scoring 40.7 to 30.8 on the Noometry Index.

Is Gemma 3 27B or Qwen2.5-Max better for coding?

Qwen2.5-Max scores higher on coding benchmarks: 41.8 versus 22.5 in the Noometry coding category.

How many benchmarks do Gemma 3 27B and Qwen2.5-Max share?

27 benchmarks have published results for both models. Gemma 3 27B has 43 scored results on Noometry and Qwen2.5-Max has 27.

Related comparisons

Go deeper