Noometry

Model comparison

Claude 3 Sonnet vs Gemma 4 26B A4B IT

Gemma 4 26B A4B IT is the stronger model overall, scoring 43.5 to 29.0 on the Noometry Index.

Last verified . 20 shared benchmarks.

Claude 3 Sonnet Anthropic

29.0

Rank #319 Confirmed

Gemma 4 26B A4B IT Google

43.5

Rank #92 Confirmed

Summary

  • They share 20 benchmarks with published results for both. Claude 3 Sonnet 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 10.7.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 2.5% for Claude 3 Sonnet 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 SonnetGemma 4 26B A4B IT
ProviderAnthropicGoogle
Noometry Index29.043.5
Released2024-02-292026-04-02
WeightsProprietaryOpen
Context window—262K
Max output—33K
Input $ / M tokens—$0.0675
Output $ / M tokens—$0.23
Results tracked3028

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

Category by category

Coding Gemma 4 26B A4B IT leads

Claude 3 Sonnet: 29.6 (#302), Gemma 4 26B A4B IT: 39.0 (#164)

BenchmarkClaude 3 SonnetGemma 4 26B A4B IT
WeirdML10.2%35.2%
LMArena Coding12231447
LMArena WebDev—1359
SciCode—40%
BigCodeBench Instruct42.7%—
BigCodeBench Complete53.8%—
ALE-Bench—927.17
HumanEval+64%—
MBPP+69.3%—

Reasoning Gemma 4 26B A4B IT leads

Claude 3 Sonnet: 20.5 (#237), Gemma 4 26B A4B IT: 21.8 (#213)

BenchmarkClaude 3 SonnetGemma 4 26B A4B IT
LMArena Hard Prompts11971439
DTBench53.6%74.9%
Epoch Capabilities Index120.7141.85
CritPt—0%
Chess Puzzles—6%
LMCA—29.7%
WinoGrande75.1%—

Math Gemma 4 26B A4B IT leads

Claude 3 Sonnet: 10.7 (#310), Gemma 4 26B A4B IT: 47.6 (#67)

BenchmarkClaude 3 SonnetGemma 4 26B A4B IT
OTIS Mock AIME 2024-20252.5%82.2%
LMArena Math12131470
MATH Level 518.2%—

Knowledge Gemma 4 26B A4B IT leads

Claude 3 Sonnet: 21.1 (#276), Gemma 4 26B A4B IT: 45.7 (#85)

BenchmarkClaude 3 SonnetGemma 4 26B A4B IT
GPQA Diamond40.6%73.2%
LMArena Expert11731447
Vectara Hallucination Rate—5.2%
MMLU75.9%—

Multimodal Gemma 4 26B A4B IT leads

Claude 3 Sonnet: 25.2 (#125), Gemma 4 26B A4B IT: 40.6 (#46)

BenchmarkClaude 3 SonnetGemma 4 26B A4B IT
LMArena Vision9841260

Multilingual Gemma 4 26B A4B IT leads

Claude 3 Sonnet: 37.8 (#234), Gemma 4 26B A4B IT: 53.1 (#71)

BenchmarkClaude 3 SonnetGemma 4 26B A4B IT
LMArena Non-English12051421
LMArena Chinese11891495
LMArena French12291460
LMArena Russian12271434
LMArena Spanish12041417
LMArena German1204—
LMArena Japanese1131—
LMArena Korean1128—

Instruction Following Gemma 4 26B A4B IT leads

Claude 3 Sonnet: 62.8 (#235), Gemma 4 26B A4B IT: 74.8 (#82)

BenchmarkClaude 3 SonnetGemma 4 26B A4B IT
LMArena Instruction Following11991420

Long Context Gemma 4 26B A4B IT leads

Claude 3 Sonnet: 36.7 (#228), Gemma 4 26B A4B IT: 43.6 (#91)

BenchmarkClaude 3 SonnetGemma 4 26B A4B IT
LMArena Longer Query12111428

Writing & Preference Gemma 4 26B A4B IT leads

Claude 3 Sonnet: 42.1 (#238), Gemma 4 26B A4B IT: 58.6 (#115)

BenchmarkClaude 3 SonnetGemma 4 26B A4B IT
LMArena Text12181434
LMArena Creative Writing11861402
LMArena Multi-Turn12271441
EQ-Bench Creative Writing—1305

Frequently asked questions

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

Gemma 4 26B A4B IT is the stronger model overall, scoring 43.5 to 29.0 on the Noometry Index.

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

Gemma 4 26B A4B IT scores higher on coding benchmarks: 39.0 versus 29.6 in the Noometry coding category.

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

20 benchmarks have published results for both models. Claude 3 Sonnet has 30 scored results on Noometry and Gemma 4 26B A4B IT has 28.

Related comparisons

Go deeper