Noometry

Model comparison

Claude 3 Haiku vs Gemma 3 27B

Gemma 3 27B is the stronger model overall, scoring 30.8 to 25.9 on the Noometry Index.

Last verified . 27 shared benchmarks.

Claude 3 Haiku Anthropic

25.9

Rank #340 Confirmed

Gemma 3 27B Google

30.8

Rank #284 Confirmed

Summary

  • They share 27 benchmarks with published results for both. Claude 3 Haiku scores higher in 2 categories and Gemma 3 27B in 7 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in writing & preference, where Gemma 3 27B leads 52.5 to 29.7.
  • The biggest single-benchmark swing is MATH Level 5: 14.9% for Claude 3 Haiku and 74% for Gemma 3 27B.
  • Gemma 3 27B has downloadable open weights; the other is API-only.

Side by side

Claude 3 HaikuGemma 3 27B
ProviderAnthropicGoogle
Noometry Index25.930.8
Released2024-03-072025-03-11
WeightsProprietaryOpen
Context window—131K
Max output—8K
Input $ / M tokens—$0.08
Output $ / M tokens—$0.16
Results tracked3743

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

Category by category

Coding Claude 3 Haiku leads

Claude 3 Haiku: 26.4 (#325), Gemma 3 27B: 22.5 (#334)

BenchmarkClaude 3 HaikuGemma 3 27B
LMArena Coding11991322
Aider Polyglot—4.9%
SciCode—21.2%
WeirdML9.8%—
BigCodeBench Instruct39.4%—
LiveBench Coding—39.9%
BigCodeBench Complete50.1%—
CadEval12%—
HumanEval+68.9%—
MBPP+68.8%—

Agentic & Tool Use Not comparable

Claude 3 Haiku: —, Gemma 3 27B: 25.1 (#110)

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

Reasoning Too close to call

Claude 3 Haiku: 16.3 (#307), Gemma 3 27B: 16.7 (#301)

BenchmarkClaude 3 HaikuGemma 3 27B
Kagi LLM Benchmark34.2%40.4%
LMArena Hard Prompts11741340
DTBench50.1%52.5%
LMCA8.8%12.3%
Epoch Capabilities Index118.35130.04
CritPt—0%
Chess Puzzles—0%
LiveBench Reasoning—43.8%
LiveBench Data Analysis—51.5%
ForecastBench53.2—
LiveBench—50%
WinoGrande74.2%—

Math Gemma 3 27B leads

Claude 3 Haiku: 9.8 (#319), Gemma 3 27B: 25.9 (#265)

BenchmarkClaude 3 HaikuGemma 3 27B
OTIS Mock AIME 2024-20251.8%22.5%
LMArena Math11881312
MATH Level 514.9%74%
LiveBench Math—55.4%

Knowledge Gemma 3 27B leads

Claude 3 Haiku: 17.3 (#285), Gemma 3 27B: 25.5 (#261)

BenchmarkClaude 3 HaikuGemma 3 27B
GPQA Diamond36.3%47.7%
Confabulations34.2%40.3%
LMArena Expert11481304
Vectara Hallucination Rate—7.4%
MMLU73.8%—

Multimodal Gemma 3 27B leads

Claude 3 Haiku: 23.6 (#128), Gemma 3 27B: 32.6 (#100)

BenchmarkClaude 3 HaikuGemma 3 27B
LMArena Vision9501164
GeoBench—52%
ScienceQA72%—

Multilingual Gemma 3 27B leads

Claude 3 Haiku: 36.0 (#243), Gemma 3 27B: 46.9 (#155)

BenchmarkClaude 3 HaikuGemma 3 27B
LMArena Non-English11781334
LMArena Chinese11551346
LMArena French11951368
LMArena German11741362
LMArena Japanese11021287
LMArena Korean11091308
LMArena Russian12041349
LMArena Spanish11661349

Instruction Following Gemma 3 27B leads

Claude 3 Haiku: 61.3 (#247), Gemma 3 27B: 70.6 (#160)

BenchmarkClaude 3 HaikuGemma 3 27B
LMArena Instruction Following11731321
LiveBench Instruction Following—74.9%

Long Context Claude 3 Haiku leads

Claude 3 Haiku: 36.1 (#237), Gemma 3 27B: 27.6 (#293)

BenchmarkClaude 3 HaikuGemma 3 27B
LMArena Longer Query11901333
Fiction.LiveBench—33.3%

Writing & Preference Gemma 3 27B leads

Claude 3 Haiku: 29.7 (#291), Gemma 3 27B: 52.5 (#168)

BenchmarkClaude 3 HaikuGemma 3 27B
LMArena Text11951358
LMArena Creative Writing11571346
EQ-Bench Creative Writing7171266
LMArena Multi-Turn11901345
Short-Story Creative Writing—79.9%
LiveBench Language—34.6%

Frequently asked questions

Is Claude 3 Haiku better than Gemma 3 27B?

Gemma 3 27B is the stronger model overall, scoring 30.8 to 25.9 on the Noometry Index.

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

Claude 3 Haiku scores higher on coding benchmarks: 26.4 versus 22.5 in the Noometry coding category.

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

27 benchmarks have published results for both models. Claude 3 Haiku has 37 scored results on Noometry and Gemma 3 27B has 43.

Related comparisons

Go deeper