Noometry

Model comparison

Deepseek Coder v2 vs Gemma 4 26B A4B IT

Gemma 4 26B A4B IT is the stronger model overall, scoring 43.5 to 35.9 on the Noometry Index.

Last verified . 14 shared benchmarks.

Deepseek Coder v2 DeepSeek

35.9

Rank #220 Confirmed

Gemma 4 26B A4B IT Google

43.5

Rank #92 Confirmed

Summary

  • They share 14 benchmarks with published results for both. Deepseek Coder v2 scores higher in 1 category and Gemma 4 26B A4B IT in 7 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in writing & preference, where Gemma 4 26B A4B IT leads 58.6 to 38.2.

Side by side

Deepseek Coder v2Gemma 4 26B A4B IT
ProviderDeepSeekGoogle
Noometry Index35.943.5
Released2024-06-172026-04-02
WeightsOpenOpen
Context window—262K
Max output—33K
Input $ / M tokens—$0.0675
Output $ / M tokens—$0.23
Results tracked2428

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

Category by category

Coding Too close to call

Deepseek Coder v2: 38.1 (#183), Gemma 4 26B A4B IT: 39.0 (#164)

BenchmarkDeepseek Coder v2Gemma 4 26B A4B IT
LMArena Coding12511447
LMArena WebDev—1359
SciCode—40%
WeirdML—35.2%
BigCodeBench Instruct48.2%—
BigCodeBench Complete59.7%—
ALE-Bench—927.17
HumanEval+82.3%—
MBPP+75.1%—

Reasoning Deepseek Coder v2 leads

Deepseek Coder v2: 23.6 (#176), Gemma 4 26B A4B IT: 21.8 (#213)

BenchmarkDeepseek Coder v2Gemma 4 26B A4B IT
LMArena Hard Prompts12071439
CritPt—0%
Chess Puzzles—6%
DTBench—74.9%
LMCA—29.7%
Epoch Capabilities Index—141.85
WinoGrande83.7%—

Math Gemma 4 26B A4B IT leads

Deepseek Coder v2: 34.9 (#190), Gemma 4 26B A4B IT: 47.6 (#67)

BenchmarkDeepseek Coder v2Gemma 4 26B A4B IT
LMArena Math12411470
OTIS Mock AIME 2024-2025—82.2%
GSM8K94.5%—

Knowledge Gemma 4 26B A4B IT leads

Deepseek Coder v2: 32.3 (#212), Gemma 4 26B A4B IT: 45.7 (#85)

BenchmarkDeepseek Coder v2Gemma 4 26B A4B IT
LMArena Expert11811447
GPQA Diamond—73.2%
Vectara Hallucination Rate—5.2%
ARC (AI2) Challenge64.3%—

Multimodal Not comparable

Deepseek Coder v2: —, Gemma 4 26B A4B IT: 40.6 (#46)

BenchmarkDeepseek Coder v2Gemma 4 26B A4B IT
LMArena Vision—1260

Multilingual Gemma 4 26B A4B IT leads

Deepseek Coder v2: 36.3 (#240), Gemma 4 26B A4B IT: 53.1 (#71)

BenchmarkDeepseek Coder v2Gemma 4 26B A4B IT
LMArena Non-English11821421
LMArena Chinese12011495
LMArena French11851460
LMArena Russian11881434
LMArena Spanish11531417
LMArena German1164—
LMArena Japanese1126—
LMArena Korean1104—

Instruction Following Gemma 4 26B A4B IT leads

Deepseek Coder v2: 61.7 (#242), Gemma 4 26B A4B IT: 74.8 (#82)

BenchmarkDeepseek Coder v2Gemma 4 26B A4B IT
LMArena Instruction Following11801420

Long Context Gemma 4 26B A4B IT leads

Deepseek Coder v2: 37.0 (#224), Gemma 4 26B A4B IT: 43.6 (#91)

BenchmarkDeepseek Coder v2Gemma 4 26B A4B IT
LMArena Longer Query12191428

Writing & Preference Gemma 4 26B A4B IT leads

Deepseek Coder v2: 38.2 (#253), Gemma 4 26B A4B IT: 58.6 (#115)

BenchmarkDeepseek Coder v2Gemma 4 26B A4B IT
LMArena Text11911434
LMArena Creative Writing11201402
LMArena Multi-Turn11771441
EQ-Bench Creative Writing—1305

Frequently asked questions

Is Deepseek Coder v2 better than Gemma 4 26B A4B IT?

Gemma 4 26B A4B IT is the stronger model overall, scoring 43.5 to 35.9 on the Noometry Index.

Is Deepseek Coder v2 or Gemma 4 26B A4B IT better for coding?

They score almost the same on coding (38.1 vs 39.0); test both on your own repository before choosing.

How many benchmarks do Deepseek Coder v2 and Gemma 4 26B A4B IT share?

14 benchmarks have published results for both models. Deepseek Coder v2 has 24 scored results on Noometry and Gemma 4 26B A4B IT has 28.

Related comparisons

Go deeper