Noometry

Model comparison

Claude 3 Sonnet vs Gemma 3 27B

Gemma 3 27B is the stronger model overall, scoring 30.5 to 28.8 on the Noometry Index.

Last verified . 23 shared benchmarks.

Claude 3 Sonnet Anthropic

28.8

Rank #311 Confirmed

Gemma 3 27B Google

30.5

Rank #277 Confirmed

Summary

  • They share 23 benchmarks with published results for both. Claude 3 Sonnet scores higher in 3 categories and Gemma 3 27B in 6 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in math, where Gemma 3 27B leads 24.4 to 10.0.
  • The biggest single-benchmark swing is MATH Level 5: 18.2% for Claude 3 Sonnet and 74% for Gemma 3 27B.
  • Gemma 3 27B has downloadable open weights; the other is API-only.

Side by side

Claude 3 SonnetGemma 3 27B
ProviderAnthropicGoogle
Noometry Index28.830.5
Released2024-02-292025-03-11
WeightsProprietaryOpen
Context window—131K
Max output—8K
Input $ / M tokens—$0.08
Output $ / M tokens—$0.16
Results tracked3043

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

Category by category

Coding Claude 3 Sonnet leads

Claude 3 Sonnet: 29.2 (#296), Gemma 3 27B: 22.1 (#329)

BenchmarkClaude 3 SonnetGemma 3 27B
LMArena Coding12231322
Aider Polyglot—4.9%
SciCode—21.2%
WeirdML10.2%—
BigCodeBench Instruct42.7%—
LiveBench Coding—39.9%
BigCodeBench Complete53.8%—
HumanEval+64%—
MBPP+69.3%—

Agentic & Tool Use Not comparable

Claude 3 Sonnet: —, Gemma 3 27B: 24.9 (#105)

BenchmarkClaude 3 SonnetGemma 3 27B
Berkeley Function Calling Leaderboard—29.5%

Reasoning Claude 3 Sonnet leads

Claude 3 Sonnet: 19.7 (#232), Gemma 3 27B: 16.3 (#297)

BenchmarkClaude 3 SonnetGemma 3 27B
LMArena Hard Prompts11971340
DTBench53.6%52.5%
Epoch Capabilities Index120.69130.04
Kagi LLM Benchmark—40.4%
CritPt—0%
Chess Puzzles—0%
LiveBench Reasoning—43.8%
LiveBench Data Analysis—51.5%
LMCA—12.3%
LiveBench—50%
WinoGrande75.1%—

Math Gemma 3 27B leads

Claude 3 Sonnet: 10.0 (#305), Gemma 3 27B: 24.4 (#261)

BenchmarkClaude 3 SonnetGemma 3 27B
OTIS Mock AIME 2024-20252.5%22.5%
LMArena Math12131312
MATH Level 518.2%74%
LiveBench Math—55.4%

Knowledge Gemma 3 27B leads

Claude 3 Sonnet: 21.1 (#271), Gemma 3 27B: 25.4 (#256)

BenchmarkClaude 3 SonnetGemma 3 27B
GPQA Diamond40.6%47.7%
LMArena Expert11731303
Confabulations—40.3%
Vectara Hallucination Rate—7.4%
MMLU75.9%—

Multimodal Gemma 3 27B leads

Claude 3 Sonnet: 24.7 (#120), Gemma 3 27B: 32.0 (#94)

BenchmarkClaude 3 SonnetGemma 3 27B
LMArena Vision9841165
GeoBench—52%

Multilingual Gemma 3 27B leads

Claude 3 Sonnet: 38.0 (#229), Gemma 3 27B: 47.0 (#150)

BenchmarkClaude 3 SonnetGemma 3 27B
LMArena Non-English12051334
LMArena Chinese11881347
LMArena French12281368
LMArena German12041362
LMArena Japanese11311287
LMArena Korean11281308
LMArena Russian12271349
LMArena Spanish12041348

Instruction Following Gemma 3 27B leads

Claude 3 Sonnet: 63.1 (#230), Gemma 3 27B: 70.8 (#155)

BenchmarkClaude 3 SonnetGemma 3 27B
LMArena Instruction Following12001321
LiveBench Instruction Following—74.9%

Long Context Claude 3 Sonnet leads

Claude 3 Sonnet: 36.7 (#223), Gemma 3 27B: 27.6 (#288)

BenchmarkClaude 3 SonnetGemma 3 27B
LMArena Longer Query12111333
Fiction.LiveBench—33.3%

Writing & Preference Gemma 3 27B leads

Claude 3 Sonnet: 42.3 (#233), Gemma 3 27B: 52.7 (#161)

BenchmarkClaude 3 SonnetGemma 3 27B
LMArena Text12181358
LMArena Creative Writing11861346
LMArena Multi-Turn12271344
Short-Story Creative Writing—79.9%
EQ-Bench Creative Writing—1266
LiveBench Language—34.6%

Frequently asked questions

Is Claude 3 Sonnet better than Gemma 3 27B?

Gemma 3 27B is the stronger model overall, scoring 30.5 to 28.8 on the Noometry Index.

Is Claude 3 Sonnet or Gemma 3 27B better for coding?

Claude 3 Sonnet scores higher on coding benchmarks: 29.2 versus 22.1 in the Noometry coding category.

How many benchmarks do Claude 3 Sonnet and Gemma 3 27B share?

23 benchmarks have published results for both models. Claude 3 Sonnet has 30 scored results on Noometry and Gemma 3 27B has 43.

Related comparisons

Go deeper