Noometry

Model comparison

Gemma 2B vs Grok 4

Grok 4 is the stronger model overall, scoring 48.1 to 29.6 on the Noometry Index.

Last verified . 12 shared benchmarks.

Gemma 2B Google

29.6

Rank #307 Confirmed

Grok 4 xAI

48.1

Rank #56 Confirmed

Summary

  • They share 12 benchmarks with published results for both. Gemma 2B scores higher in 0 categories and Grok 4 in 7 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in writing & preference, where Grok 4 leads 58.5 to 24.0.
  • Gemma 2B has downloadable open weights; the other is API-only.

Side by side

Gemma 2BGrok 4
ProviderGooglexAI
Noometry Index29.648.1
Released2024-02-212025-07-09
WeightsOpenProprietary
Context window——
Max output——
Input $ / M tokens——
Output $ / M tokens——
Results tracked2348

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

Category by category

Coding Grok 4 leads

Gemma 2B: 29.4 (#305), Grok 4: 50.3 (#46)

BenchmarkGemma 2BGrok 4
LMArena Coding10101408
Aider Polyglot—79.6%
WeirdML—45.7%
HumanEval+20.7%—
MBPP+34.1%—

Agentic & Tool Use Not comparable

Gemma 2B: —, Grok 4: 32.3 (#68)

BenchmarkGemma 2BGrok 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 2B: 18.8 (#275), Grok 4: 36.7 (#65)

BenchmarkGemma 2BGrok 4
LMArena Hard Prompts9891409
Epoch Capabilities Index94.2146.44
ARC-AGI-2—16%
SimpleBench—60.5%
Kagi LLM Benchmark—73.6%
ARC-AGI-1—66.7%
Chess Puzzles—28%
BIG-Bench Hard35.2%—
ForecastBench—60.9
HellaSwag71.4%—
PIQA77.3%—
WinoGrande65.4%—

Math Grok 4 leads

Gemma 2B: 30.0 (#239), Grok 4: 48.4 (#64)

BenchmarkGemma 2BGrok 4
LMArena Math10091422
OTIS Mock AIME 2024-2025—84%
Omni-MATH—60.3%
FrontierMath (Feb 2025 set)—19.7%
FrontierMath Tier 4 (v1)—2.1%
GSM8K17.7%—

Knowledge Not comparable

Gemma 2B: —, Grok 4: 53.8 (#55)

BenchmarkGemma 2BGrok 4
GPQA Diamond—87%
MMLU-Pro—85.1%
Confabulations—12.4%
GPQA (HELM)—72.7%
LMArena Expert—1415
ARC (AI2) Challenge42.1%—
BoolQ69.4%—
MMLU42.3%—
TriviaQA53.2%—

Multimodal Not comparable

Gemma 2B: —, Grok 4: 33.7 (#94)

BenchmarkGemma 2BGrok 4
LMArena Vision—1210
GeoBench—45%

Multilingual Grok 4 leads

Gemma 2B: 23.0 (#294), Grok 4: 51.8 (#103)

BenchmarkGemma 2BGrok 4
LMArena Non-English9581403
LMArena Chinese9861427
LMArena Russian9371410
LMArena French—1418
LMArena German—1429
LMArena Japanese—1394
LMArena Korean—1377
LMArena Spanish—1420

Instruction Following Grok 4 leads

Gemma 2B: 48.5 (#302), Grok 4: 79.2 (#5)

BenchmarkGemma 2BGrok 4
LMArena Instruction Following9701387
IFEval—94.9%

Long Context Grok 4 leads

Gemma 2B: 29.9 (#291), Grok 4: 63.1 (#4)

BenchmarkGemma 2BGrok 4
LMArena Longer Query9811409
Fiction.LiveBench—94.4%

Writing & Preference Grok 4 leads

Gemma 2B: 24.0 (#308), Grok 4: 58.5 (#116)

BenchmarkGemma 2BGrok 4
LMArena Text10021411
LMArena Creative Writing9871397
LMArena Multi-Turn9451416
Short-Story Creative Writing—76.9%
WildBench—79.7%

Frequently asked questions

Is Gemma 2B better than Grok 4?

Grok 4 is the stronger model overall, scoring 48.1 to 29.6 on the Noometry Index.

Is Gemma 2B or Grok 4 better for coding?

Grok 4 scores higher on coding benchmarks: 50.3 versus 29.4 in the Noometry coding category.

How many benchmarks do Gemma 2B and Grok 4 share?

12 benchmarks have published results for both models. Gemma 2B has 23 scored results on Noometry and Grok 4 has 48.

Related comparisons

Go deeper