Noometry

Model comparison

Claude 3 Haiku vs Gemma 4 26B A4B IT

Gemma 4 26B A4B IT is the stronger model overall, scoring 43.5 to 25.9 on the Noometry Index.

Last verified . 22 shared benchmarks.

Claude 3 Haiku Anthropic

25.9

Rank #340 Confirmed

Gemma 4 26B A4B IT Google

43.5

Rank #92 Confirmed

Summary

  • They share 22 benchmarks with published results for both. Claude 3 Haiku scores higher in 0 categories and Gemma 4 26B A4B IT in 9 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in math, where Gemma 4 26B A4B IT leads 47.6 to 9.8.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 1.8% for Claude 3 Haiku and 82.2% for Gemma 4 26B A4B IT.
  • Gemma 4 26B A4B IT has downloadable open weights; the other is API-only.

Side by side

Claude 3 HaikuGemma 4 26B A4B IT
ProviderAnthropicGoogle
Noometry Index25.943.5
Released2024-03-072026-04-02
WeightsProprietaryOpen
Context window—262K
Max output—33K
Input $ / M tokens—$0.09
Output $ / M tokens—$0.30
Results tracked3728

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

Category by category

Coding Gemma 4 26B A4B IT leads

Claude 3 Haiku: 26.4 (#325), Gemma 4 26B A4B IT: 39.0 (#164)

BenchmarkClaude 3 HaikuGemma 4 26B A4B IT
WeirdML9.8%35.2%
LMArena Coding11991447
LMArena WebDev—1359
SciCode—40%
BigCodeBench Instruct39.4%—
BigCodeBench Complete50.1%—
CadEval12%—
ALE-Bench—927.17
HumanEval+68.9%—
MBPP+68.8%—

Reasoning Gemma 4 26B A4B IT leads

Claude 3 Haiku: 16.3 (#307), Gemma 4 26B A4B IT: 21.8 (#213)

BenchmarkClaude 3 HaikuGemma 4 26B A4B IT
LMArena Hard Prompts11741439
DTBench50.1%74.9%
LMCA8.8%29.7%
Epoch Capabilities Index118.35141.85
Kagi LLM Benchmark34.2%—
CritPt—0%
Chess Puzzles—6%
ForecastBench53.2—
WinoGrande74.2%—

Math Gemma 4 26B A4B IT leads

Claude 3 Haiku: 9.8 (#319), Gemma 4 26B A4B IT: 47.6 (#67)

BenchmarkClaude 3 HaikuGemma 4 26B A4B IT
OTIS Mock AIME 2024-20251.8%82.2%
LMArena Math11881470
MATH Level 514.9%—

Knowledge Gemma 4 26B A4B IT leads

Claude 3 Haiku: 17.3 (#285), Gemma 4 26B A4B IT: 45.7 (#85)

BenchmarkClaude 3 HaikuGemma 4 26B A4B IT
GPQA Diamond36.3%73.2%
LMArena Expert11481447
Confabulations34.2%—
Vectara Hallucination Rate—5.2%
MMLU73.8%—

Multimodal Gemma 4 26B A4B IT leads

Claude 3 Haiku: 23.6 (#128), Gemma 4 26B A4B IT: 40.6 (#46)

BenchmarkClaude 3 HaikuGemma 4 26B A4B IT
LMArena Vision9501260
ScienceQA72%—

Multilingual Gemma 4 26B A4B IT leads

Claude 3 Haiku: 36.0 (#243), Gemma 4 26B A4B IT: 53.1 (#71)

BenchmarkClaude 3 HaikuGemma 4 26B A4B IT
LMArena Non-English11781421
LMArena Chinese11551495
LMArena French11951460
LMArena Russian12041434
LMArena Spanish11661417
LMArena German1174—
LMArena Japanese1102—
LMArena Korean1109—

Instruction Following Gemma 4 26B A4B IT leads

Claude 3 Haiku: 61.3 (#247), Gemma 4 26B A4B IT: 74.8 (#82)

BenchmarkClaude 3 HaikuGemma 4 26B A4B IT
LMArena Instruction Following11731420

Long Context Gemma 4 26B A4B IT leads

Claude 3 Haiku: 36.1 (#237), Gemma 4 26B A4B IT: 43.6 (#91)

BenchmarkClaude 3 HaikuGemma 4 26B A4B IT
LMArena Longer Query11901428

Writing & Preference Gemma 4 26B A4B IT leads

Claude 3 Haiku: 29.7 (#291), Gemma 4 26B A4B IT: 58.6 (#115)

BenchmarkClaude 3 HaikuGemma 4 26B A4B IT
LMArena Text11951434
LMArena Creative Writing11571402
EQ-Bench Creative Writing7171305
LMArena Multi-Turn11901441

Frequently asked questions

Is Claude 3 Haiku better than Gemma 4 26B A4B IT?

Gemma 4 26B A4B IT is the stronger model overall, scoring 43.5 to 25.9 on the Noometry Index.

Is Claude 3 Haiku or Gemma 4 26B A4B IT better for coding?

Gemma 4 26B A4B IT scores higher on coding benchmarks: 39.0 versus 26.4 in the Noometry coding category.

How many benchmarks do Claude 3 Haiku and Gemma 4 26B A4B IT share?

22 benchmarks have published results for both models. Claude 3 Haiku has 37 scored results on Noometry and Gemma 4 26B A4B IT has 28.

Related comparisons

Go deeper