Noometry

Model comparison

Claude 3 Haiku vs Gemma 2 27B

Gemma 2 27B is the stronger model overall, scoring 29.2 to 25.7 on the Noometry Index.

Last verified . 27 shared benchmarks.

Claude 3 Haiku Anthropic

25.7

Rank #333 Confirmed

Gemma 2 27B Google

29.2

Rank #302 Confirmed

Summary

  • They share 27 benchmarks with published results for both. Claude 3 Haiku scores higher in 2 categories and Gemma 2 27B in 6 categories; 5 gaps are clear of the uncertainty.
  • The widest gap is in writing & preference, where Gemma 2 27B leads 44.4 to 29.8.
  • The biggest single-benchmark swing is MATH Level 5: 14.9% for Claude 3 Haiku and 27.9% for Gemma 2 27B.
  • Gemma 2 27B has downloadable open weights; the other is API-only.

Side by side

Claude 3 HaikuGemma 2 27B
ProviderAnthropicGoogle
Noometry Index25.729.2
Released2024-03-072024-06-24
WeightsProprietaryOpen
Context window—8K
Max output—2K
Input $ / M tokens—$0.65
Output $ / M tokens—$0.65
Results tracked3734

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

Category by category

Coding Gemma 2 27B leads

Claude 3 Haiku: 26.1 (#320), Gemma 2 27B: 33.5 (#243)

BenchmarkClaude 3 HaikuGemma 2 27B
BigCodeBench Instruct39.4%42.8%
LMArena Coding11991211
BigCodeBench Complete50.1%52.5%
WeirdML9.8%—
LiveBench Coding—36%
CadEval12%—
HumanEval+68.9%—
MBPP+68.8%—

Reasoning Too close to call

Claude 3 Haiku: 15.7 (#303), Gemma 2 27B: 14.8 (#313)

BenchmarkClaude 3 HaikuGemma 2 27B
LMArena Hard Prompts11741199
DTBench50.1%48%
LMCA8.8%7.1%
Epoch Capabilities Index118.3122.06
Kagi LLM Benchmark34.2%—
LiveBench Reasoning—28.1%
LiveBench Data Analysis—47.9%
ForecastBench53.2—
LiveBench—38.2%
WinoGrande74.2%—

Math Too close to call

Claude 3 Haiku: 9.2 (#313), Gemma 2 27B: 10.0 (#306)

BenchmarkClaude 3 HaikuGemma 2 27B
OTIS Mock AIME 2024-20251.8%1.4%
LMArena Math11881212
MATH Level 514.9%27.9%
LiveBench Math—26.5%

Knowledge Gemma 2 27B leads

Claude 3 Haiku: 17.3 (#280), Gemma 2 27B: 18.9 (#275)

BenchmarkClaude 3 HaikuGemma 2 27B
GPQA Diamond36.3%36.5%
Confabulations34.2%27.1%
LMArena Expert11481172
MMLU73.8%75.7%

Multimodal Not comparable

Claude 3 Haiku: 23.1 (#123), Gemma 2 27B: —

BenchmarkClaude 3 HaikuGemma 2 27B
LMArena Vision950—
ScienceQA72%—

Multilingual Gemma 2 27B leads

Claude 3 Haiku: 36.1 (#238), Gemma 2 27B: 38.8 (#221)

BenchmarkClaude 3 HaikuGemma 2 27B
LMArena Non-English11781217
LMArena Chinese11551221
LMArena French11941246
LMArena German11741209
LMArena Japanese11021175
LMArena Korean11081174
LMArena Russian12041234
LMArena Spanish11651228

Instruction Following Too close to call

Claude 3 Haiku: 61.5 (#242), Gemma 2 27B: 60.7 (#244)

BenchmarkClaude 3 HaikuGemma 2 27B
LMArena Instruction Following11741206
LiveBench Instruction Following—58.1%

Long Context Gemma 2 27B leads

Claude 3 Haiku: 36.1 (#232), Gemma 2 27B: 37.3 (#213)

BenchmarkClaude 3 HaikuGemma 2 27B
LMArena Longer Query11911231

Writing & Preference Gemma 2 27B leads

Claude 3 Haiku: 29.8 (#286), Gemma 2 27B: 44.4 (#220)

BenchmarkClaude 3 HaikuGemma 2 27B
LMArena Text11951231
LMArena Creative Writing11571241
LMArena Multi-Turn11901224
EQ-Bench Creative Writing717—
LiveBench Language—32.6%

Frequently asked questions

Is Claude 3 Haiku better than Gemma 2 27B?

Gemma 2 27B is the stronger model overall, scoring 29.2 to 25.7 on the Noometry Index.

Is Claude 3 Haiku or Gemma 2 27B better for coding?

Gemma 2 27B scores higher on coding benchmarks: 33.5 versus 26.1 in the Noometry coding category.

How many benchmarks do Claude 3 Haiku and Gemma 2 27B share?

27 benchmarks have published results for both models. Claude 3 Haiku has 37 scored results on Noometry and Gemma 2 27B has 34.

Related comparisons

Go deeper