Noometry

Model comparison

Claude 3.5 Haiku vs Gemma 3n E4b IT

Gemma 3n E4b IT is the stronger model overall, scoring 36.7 to 28.9 on the Noometry Index.

Last verified . 17 shared benchmarks.

Claude 3.5 Haiku Anthropic

28.9

Rank #309 Confirmed

Gemma 3n E4b IT Google

36.7

Rank #203 Confirmed

Summary

  • They share 17 benchmarks with published results for both. Claude 3.5 Haiku scores higher in 0 categories and Gemma 3n E4b IT in 8 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in math, where Gemma 3n E4b IT leads 32.5 to 13.7.
  • Gemma 3n E4b IT has downloadable open weights; the other is API-only.

Side by side

Claude 3.5 HaikuGemma 3n E4b IT
ProviderAnthropicGoogle
Noometry Index28.936.7
Released2024-10-222025-05-20
WeightsProprietaryOpen
Context window—33K
Max output—33K
Input $ / M tokens—$0.06
Output $ / M tokens—$0.12
Results tracked4918

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

Category by category

Coding Gemma 3n E4b IT leads

Claude 3.5 Haiku: 32.6 (#258), Gemma 3n E4b IT: 36.4 (#193)

BenchmarkClaude 3.5 HaikuGemma 3n E4b IT
LMArena Coding12871269
Aider Polyglot28%—
SciCode27.4%—
WeirdML30.7%—
BigCodeBench Instruct46.1%—
LiveBench Coding51.4%—
BigCodeBench Complete59%—
CadEval32%—

Agentic & Tool Use Not comparable

Claude 3.5 Haiku: 27.7 (#90), Gemma 3n E4b IT: —

BenchmarkClaude 3.5 HaikuGemma 3n E4b IT
BALROG19.3%—

Reasoning Gemma 3n E4b IT leads

Claude 3.5 Haiku: 17.1 (#286), Gemma 3n E4b IT: 19.2 (#239)

BenchmarkClaude 3.5 HaikuGemma 3n E4b IT
LMArena Hard Prompts12511284
Kagi LLM Benchmark—31.5%
CritPt0%—
LiveBench Reasoning28.1%—
DTBench56.7%—
LiveBench Data Analysis48.5%—
Epoch Capabilities Index127.15—
LiveBench43.5%—

Math Gemma 3n E4b IT leads

Claude 3.5 Haiku: 13.7 (#294), Gemma 3n E4b IT: 32.5 (#186)

BenchmarkClaude 3.5 HaikuGemma 3n E4b IT
LMArena Math12441251
OTIS Mock AIME 2024-20254.3%—
Omni-MATH22.4%—
LiveBench Math35.5%—
MATH Level 546.4%—
FrontierMath (Feb 2025 set)0.3%—

Knowledge Gemma 3n E4b IT leads

Claude 3.5 Haiku: 18.7 (#276), Gemma 3n E4b IT: 33.6 (#193)

BenchmarkClaude 3.5 HaikuGemma 3n E4b IT
LMArena Expert12081245
GPQA Diamond38.1%—
MMLU-Pro60.5%—
Confabulations36.7%—
GPQA (HELM)36.3%—
MMLU74.3%—

Multimodal Not comparable

Claude 3.5 Haiku: 26.3 (#113), Gemma 3n E4b IT: —

BenchmarkClaude 3.5 HaikuGemma 3n E4b IT
LMArena Vision1092—
GeoBench34%—

Multilingual Gemma 3n E4b IT leads

Claude 3.5 Haiku: 40.2 (#213), Gemma 3n E4b IT: 43.5 (#179)

BenchmarkClaude 3.5 HaikuGemma 3n E4b IT
LMArena Non-English12381285
LMArena Chinese12291310
LMArena French12621330
LMArena German12371312
LMArena Japanese11751274
LMArena Korean11721259
LMArena Russian12531288
LMArena Spanish12611305

Instruction Following Gemma 3n E4b IT leads

Claude 3.5 Haiku: 63.1 (#229), Gemma 3n E4b IT: 66.3 (#205)

BenchmarkClaude 3.5 HaikuGemma 3n E4b IT
LMArena Instruction Following12411255
LiveBench Instruction Following61.9%—
IFEval79.2%—

Long Context Too close to call

Claude 3.5 Haiku: 38.3 (#195), Gemma 3n E4b IT: 38.8 (#185)

BenchmarkClaude 3.5 HaikuGemma 3n E4b IT
LMArena Longer Query12611277

Writing & Preference Gemma 3n E4b IT leads

Claude 3.5 Haiku: 42.9 (#228), Gemma 3n E4b IT: 50.3 (#181)

BenchmarkClaude 3.5 HaikuGemma 3n E4b IT
LMArena Text12551306
LMArena Creative Writing12331287
LMArena Multi-Turn12651276
Short-Story Creative Writing73.5%—
EQ-Bench Creative Writing1146—
WildBench76%—
LiveBench Language35.4%—

Frequently asked questions

Is Claude 3.5 Haiku better than Gemma 3n E4b IT?

Gemma 3n E4b IT is the stronger model overall, scoring 36.7 to 28.9 on the Noometry Index.

Is Claude 3.5 Haiku or Gemma 3n E4b IT better for coding?

Gemma 3n E4b IT scores higher on coding benchmarks: 36.4 versus 32.6 in the Noometry coding category.

How many benchmarks do Claude 3.5 Haiku and Gemma 3n E4b IT share?

17 benchmarks have published results for both models. Claude 3.5 Haiku has 49 scored results on Noometry and Gemma 3n E4b IT has 18.

Related comparisons

Go deeper