Noometry

Model comparison

Gemini 4 Argon vs Grok-3 mini

Gemini 4 Argon is the stronger model overall, scoring 56.5 to 41.2 on the Noometry Index.

Last verified . 13 shared benchmarks.

Gemini 4 Argon Google

56.5

Rank #24 Confirmed

Grok-3 mini xAI

41.2

Rank #141 Confirmed

Summary

  • They share 13 benchmarks with published results for both. Gemini 4 Argon scores higher in 7 categories and Grok-3 mini in 1 category; 8 gaps are clear of the uncertainty.
  • The widest gap is in math, where Gemini 4 Argon leads 73.9 to 42.1.

Side by side

Gemini 4 ArgonGrok-3 mini
ProviderGooglexAI
Noometry Index56.541.2
Released2026-09-302025-04-09
WeightsProprietaryProprietary
Context window——
Max output——
Input $ / M tokens——
Output $ / M tokens——
Results tracked2135

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

Category by category

Coding Gemini 4 Argon leads

Gemini 4 Argon: 62.0 (#9), Grok-3 mini: 40.8 (#131)

BenchmarkGemini 4 ArgonGrok-3 mini
LMArena Coding15501379
Aider Polyglot—49.3%
LMArena WebDev1678—
FrontierSWE55%—
SciCode61.8%—
WeirdML—42.6%

Agentic & Tool Use Not comparable

Gemini 4 Argon: 49.2 (#8), Grok-3 mini: —

BenchmarkGemini 4 ArgonGrok-3 mini
APEX-Agents82.2%—
Vending-Bench 213,718—

Reasoning Gemini 4 Argon leads

Gemini 4 Argon: 44.2 (#47), Grok-3 mini: 13.6 (#334)

BenchmarkGemini 4 ArgonGrok-3 mini
LMArena Hard Prompts15481375
ARC-AGI-2—0.4%
Kagi LLM Benchmark—61.3%
ARC-AGI-1—16.5%
CritPt27.1%—
Epoch Capabilities Index—140.35

Math Gemini 4 Argon leads

Gemini 4 Argon: 73.9 (#17), Grok-3 mini: 42.1 (#85)

BenchmarkGemini 4 ArgonGrok-3 mini
LMArena Math15361386
OTIS Mock AIME 2024-2025—77.8%
ProofBench99%—
Omni-MATH—31.8%
MATH Level 5—90.9%
FrontierMath (Feb 2025 set)—5.9%

Knowledge Grok-3 mini leads

Gemini 4 Argon: 43.9 (#89), Grok-3 mini: 46.4 (#81)

BenchmarkGemini 4 ArgonGrok-3 mini
LMArena Expert15531395
GPQA Diamond—76.3%
MMLU-Pro—79.9%
Confabulations—10.8%
GPQA (HELM)—67.5%

Multimodal Not comparable

Gemini 4 Argon: 46.5 (#14), Grok-3 mini: —

BenchmarkGemini 4 ArgonGrok-3 mini
Blueprint-Bench 254.4%—

Multilingual Gemini 4 Argon leads

Gemini 4 Argon: 60.3 (#1), Grok-3 mini: 48.1 (#145)

BenchmarkGemini 4 ArgonGrok-3 mini
LMArena Non-English15231352
LMArena Chinese16101387
LMArena Russian15371353
LMArena Spanish14971381
LMArena French—1357
LMArena German—1349
LMArena Japanese—1342
LMArena Korean—1335

Instruction Following Gemini 4 Argon leads

Gemini 4 Argon: 80.1 (#2), Grok-3 mini: 78.5 (#9)

BenchmarkGemini 4 ArgonGrok-3 mini
LMArena Instruction Following15381357
IFEval—95.1%

Long Context Gemini 4 Argon leads

Gemini 4 Argon: 47.6 (#15), Grok-3 mini: 41.0 (#147)

BenchmarkGemini 4 ArgonGrok-3 mini
LMArena Longer Query15491372
Fiction.LiveBench—66.7%

Writing & Preference Gemini 4 Argon leads

Gemini 4 Argon: 71.4 (#19), Grok-3 mini: 52.5 (#169)

BenchmarkGemini 4 ArgonGrok-3 mini
LMArena Text15341370
LMArena Creative Writing15311342
LMArena Multi-Turn15571355
Short-Story Creative Writing—73.5%
WildBench—65.1%

Frequently asked questions

Is Gemini 4 Argon better than Grok-3 mini?

Gemini 4 Argon is the stronger model overall, scoring 56.5 to 41.2 on the Noometry Index.

Is Gemini 4 Argon or Grok-3 mini better for coding?

Gemini 4 Argon scores higher on coding benchmarks: 62.0 versus 40.8 in the Noometry coding category.

How many benchmarks do Gemini 4 Argon and Grok-3 mini share?

13 benchmarks have published results for both models. Gemini 4 Argon has 21 scored results on Noometry and Grok-3 mini has 35.

Related comparisons

Go deeper