Noometry

Model comparison

Gemma 7B vs Grok 4

Grok 4 is the stronger model overall, scoring 48.1 to 30.0 on the Noometry Index.

Last verified . 14 shared benchmarks.

Gemma 7B Google

30.0

Rank #299 Confirmed

Grok 4 xAI

48.1

Rank #56 Confirmed

Summary

  • They share 14 benchmarks with published results for both. Gemma 7B scores higher in 0 categories and Grok 4 in 8 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in long context, where Grok 4 leads 63.1 to 31.1.
  • Gemma 7B has downloadable open weights; the other is API-only.

Side by side

Gemma 7BGrok 4
ProviderGooglexAI
Noometry Index30.048.1
Released2024-02-212025-07-09
WeightsOpenProprietary
Context window——
Max output——
Input $ / M tokens——
Output $ / M tokens——
Results tracked2748

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

Category by category

Coding Grok 4 leads

Gemma 7B: 30.5 (#294), Grok 4: 50.3 (#46)

BenchmarkGemma 7BGrok 4
LMArena Coding10481408
Aider Polyglot—79.6%
WeirdML—45.7%
HumanEval+28.7%—
MBPP+43.4%—

Agentic & Tool Use Not comparable

Gemma 7B: —, Grok 4: 32.3 (#68)

BenchmarkGemma 7BGrok 4
Terminal-Bench—27.2%
Berkeley Function Calling Leaderboard—63%
GDPval—21.1%
Cybench—43%
DeepResearch Bench—47.3%
BALROG—43.6%
LMArena Search—1142
METR Time Horizons—66.6%

Reasoning Grok 4 leads

Gemma 7B: 19.9 (#249), Grok 4: 36.7 (#65)

BenchmarkGemma 7BGrok 4
LMArena Hard Prompts10421409
Epoch Capabilities Index111.99146.44
ARC-AGI-2—16%
SimpleBench—60.5%
Kagi LLM Benchmark—73.6%
ARC-AGI-1—66.7%
Chess Puzzles—28%
Adversarial NLI48.7%—
BIG-Bench Hard55.1%—
ForecastBench—60.9
HellaSwag82.2%—
PIQA81.2%—
WinoGrande79%—

Math Grok 4 leads

Gemma 7B: 31.2 (#228), Grok 4: 48.4 (#64)

BenchmarkGemma 7BGrok 4
LMArena Math10661422
OTIS Mock AIME 2024-2025—84%
Omni-MATH—60.3%
FrontierMath (Feb 2025 set)—19.7%
FrontierMath Tier 4 (v1)—2.1%
GSM8K46.4%—

Knowledge Grok 4 leads

Gemma 7B: 27.3 (#252), Grok 4: 53.8 (#55)

BenchmarkGemma 7BGrok 4
LMArena Expert10011415
GPQA Diamond—87%
MMLU-Pro—85.1%
Confabulations—12.4%
GPQA (HELM)—72.7%
ARC (AI2) Challenge78.3%—
BoolQ83.2%—
MMLU66.1%—
OpenBookQA78.6%—
TriviaQA72.3%—

Multimodal Not comparable

Gemma 7B: —, Grok 4: 33.7 (#94)

BenchmarkGemma 7BGrok 4
LMArena Vision—1210
GeoBench—45%

Multilingual Grok 4 leads

Gemma 7B: 25.1 (#287), Grok 4: 51.8 (#103)

BenchmarkGemma 7BGrok 4
LMArena Non-English9991403
LMArena Chinese10351427
LMArena French10251418
LMArena Russian9931410
LMArena German—1429
LMArena Japanese—1394
LMArena Korean—1377
LMArena Spanish—1420

Instruction Following Grok 4 leads

Gemma 7B: 51.5 (#295), Grok 4: 79.2 (#5)

BenchmarkGemma 7BGrok 4
LMArena Instruction Following10171387
IFEval—94.9%

Long Context Grok 4 leads

Gemma 7B: 31.1 (#282), Grok 4: 63.1 (#4)

BenchmarkGemma 7BGrok 4
LMArena Longer Query10221409
Fiction.LiveBench—94.4%

Writing & Preference Grok 4 leads

Gemma 7B: 27.1 (#302), Grok 4: 58.5 (#116)

BenchmarkGemma 7BGrok 4
LMArena Text10561411
LMArena Creative Writing10241397
LMArena Multi-Turn9631416
Short-Story Creative Writing—76.9%
WildBench—79.7%

Frequently asked questions

Is Gemma 7B better than Grok 4?

Grok 4 is the stronger model overall, scoring 48.1 to 30.0 on the Noometry Index.

Is Gemma 7B or Grok 4 better for coding?

Grok 4 scores higher on coding benchmarks: 50.3 versus 30.5 in the Noometry coding category.

How many benchmarks do Gemma 7B and Grok 4 share?

14 benchmarks have published results for both models. Gemma 7B has 27 scored results on Noometry and Grok 4 has 48.

Related comparisons

Go deeper