Noometry

Model comparison

Claude 3 Haiku vs Gemma 2 27B

Gemma 2 27B is the stronger model overall, scoring 29.4 to 25.9 on the Noometry Index.

Last verified . 27 shared benchmarks.

Claude 3 Haiku Anthropic

25.9

Rank #340 Confirmed

Gemma 2 27B Google

29.4

Rank #312 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 44.2 to 29.7.
  • 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 Index25.929.4
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: 26.4 (#325), Gemma 2 27B: 34.1 (#246)

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: 16.3 (#307), Gemma 2 27B: 15.3 (#315)

BenchmarkClaude 3 HaikuGemma 2 27B
LMArena Hard Prompts11741198
DTBench50.1%48%
LMCA8.8%7.1%
Epoch Capabilities Index118.35122.08
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: 9.8 (#319), Gemma 2 27B: 10.7 (#311)

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 (#285), Gemma 2 27B: 19.0 (#280)

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: 23.6 (#128), Gemma 2 27B: —

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

Multilingual Gemma 2 27B leads

Claude 3 Haiku: 36.0 (#243), Gemma 2 27B: 38.6 (#226)

BenchmarkClaude 3 HaikuGemma 2 27B
LMArena Non-English11781217
LMArena Chinese11551221
LMArena French11951247
LMArena German11741209
LMArena Japanese11021175
LMArena Korean11091174
LMArena Russian12041234
LMArena Spanish11661228

Instruction Following Too close to call

Claude 3 Haiku: 61.3 (#247), Gemma 2 27B: 60.5 (#249)

BenchmarkClaude 3 HaikuGemma 2 27B
LMArena Instruction Following11731206
LiveBench Instruction Following—58.1%

Long Context Gemma 2 27B leads

Claude 3 Haiku: 36.1 (#237), Gemma 2 27B: 37.3 (#218)

BenchmarkClaude 3 HaikuGemma 2 27B
LMArena Longer Query11901231

Writing & Preference Gemma 2 27B leads

Claude 3 Haiku: 29.7 (#291), Gemma 2 27B: 44.2 (#225)

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 29.4 to 25.9 on the Noometry Index.

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

Gemma 2 27B scores higher on coding benchmarks: 34.1 versus 26.4 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