Noometry

Model comparison

Gemma 3 4B vs Grok-3 mini

Grok-3 mini is the stronger model overall, scoring 41.2 to 28.1 on the Noometry Index.

Last verified . 16 shared benchmarks.

Gemma 3 4B Google

28.1

Rank #326 Confirmed

Grok-3 mini xAI

41.2

Rank #141 Confirmed

Summary

  • They share 16 benchmarks with published results for both. Gemma 3 4B scores higher in 0 categories and Grok-3 mini in 8 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Grok-3 mini leads 46.4 to 11.8.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 7.5% for Gemma 3 4B and 77.8% for Grok-3 mini.
  • Gemma 3 4B has downloadable open weights; the other is API-only.

Side by side

Gemma 3 4BGrok-3 mini
ProviderGooglexAI
Noometry Index28.141.2
Released2025-03-122025-04-09
WeightsOpenProprietary
Context window131K—
Max output4K—
Input $ / M tokens$0.04—
Output $ / M tokens$0.08—
Results tracked2235

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

Category by category

Coding Grok-3 mini leads

Gemma 3 4B: 35.9 (#215), Grok-3 mini: 40.8 (#131)

BenchmarkGemma 3 4BGrok-3 mini
LMArena Coding12301379
Aider Polyglot—49.3%
WeirdML—42.6%

Agentic & Tool Use Not comparable

Gemma 3 4B: 20.9 (#142), Grok-3 mini: —

BenchmarkGemma 3 4BGrok-3 mini
Berkeley Function Calling Leaderboard19.6%—

Reasoning Too close to call

Gemma 3 4B: 13.2 (#335), Grok-3 mini: 13.6 (#334)

BenchmarkGemma 3 4BGrok-3 mini
Kagi LLM Benchmark25.2%61.3%
LMArena Hard Prompts12531375
Epoch Capabilities Index116.02140.35
ARC-AGI-2—0.4%
ARC-AGI-1—16.5%
Chess Puzzles0%—
DTBench50.9%—
LMCA2.8%—

Math Grok-3 mini leads

Gemma 3 4B: 16.8 (#292), Grok-3 mini: 42.1 (#85)

BenchmarkGemma 3 4BGrok-3 mini
OTIS Mock AIME 2024-20257.5%77.8%
LMArena Math12391386
Omni-MATH—31.8%
MATH Level 5—90.9%
FrontierMath (Feb 2025 set)—5.9%

Knowledge Grok-3 mini leads

Gemma 3 4B: 11.8 (#299), Grok-3 mini: 46.4 (#81)

BenchmarkGemma 3 4BGrok-3 mini
GPQA Diamond23.2%76.3%
LMArena Expert12231395
MMLU-Pro—79.9%
Confabulations—10.8%
Vectara Hallucination Rate6.4%—
GPQA (HELM)—67.5%

Multilingual Grok-3 mini leads

Gemma 3 4B: 42.5 (#194), Grok-3 mini: 48.1 (#145)

BenchmarkGemma 3 4BGrok-3 mini
LMArena Non-English12731352
LMArena German12811349
LMArena Russian12941353
LMArena Chinese—1387
LMArena French—1357
LMArena Japanese—1342
LMArena Korean—1335
LMArena Spanish—1381

Instruction Following Grok-3 mini leads

Gemma 3 4B: 65.2 (#225), Grok-3 mini: 78.5 (#9)

BenchmarkGemma 3 4BGrok-3 mini
LMArena Instruction Following12391357
IFEval—95.1%

Long Context Grok-3 mini leads

Gemma 3 4B: 38.7 (#194), Grok-3 mini: 41.0 (#147)

BenchmarkGemma 3 4BGrok-3 mini
LMArena Longer Query12731372
Fiction.LiveBench—66.7%

Writing & Preference Grok-3 mini leads

Gemma 3 4B: 42.0 (#239), Grok-3 mini: 52.5 (#169)

BenchmarkGemma 3 4BGrok-3 mini
LMArena Text12911370
LMArena Creative Writing12711342
LMArena Multi-Turn12551355
Short-Story Creative Writing—73.5%
EQ-Bench Creative Writing1068—
WildBench—65.1%

Frequently asked questions

Is Gemma 3 4B better than Grok-3 mini?

Grok-3 mini is the stronger model overall, scoring 41.2 to 28.1 on the Noometry Index.

Is Gemma 3 4B or Grok-3 mini better for coding?

Grok-3 mini scores higher on coding benchmarks: 40.8 versus 35.9 in the Noometry coding category.

How many benchmarks do Gemma 3 4B and Grok-3 mini share?

16 benchmarks have published results for both models. Gemma 3 4B has 22 scored results on Noometry and Grok-3 mini has 35.

Related comparisons

Go deeper