Noometry

Model comparison

GPT-6 Luna vs Grok-3 mini

GPT-6 Luna is the stronger model overall, scoring 53.3 to 41.2 on the Noometry Index.

Last verified . 22 shared benchmarks.

GPT-6 Luna OpenAI

53.3

Rank #36 Confirmed

Grok-3 mini xAI

41.2

Rank #141 Confirmed

Summary

  • They share 22 benchmarks with published results for both. GPT-6 Luna scores higher in 7 categories and Grok-3 mini in 1 category; 8 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where GPT-6 Luna leads 48.2 to 13.6.
  • The biggest single-benchmark swing is ARC-AGI-1: 86.7% for GPT-6 Luna and 16.5% for Grok-3 mini.

Side by side

GPT-6 LunaGrok-3 mini
ProviderOpenAIxAI
Noometry Index53.341.2
Released2026-09-222025-04-09
WeightsProprietaryProprietary
Context window1.05M—
Max output128K—
Input $ / M tokens$0.10—
Output $ / M tokens$0.50—
Results tracked4235

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

Category by category

Coding GPT-6 Luna leads

GPT-6 Luna: 55.5 (#25), Grok-3 mini: 40.8 (#131)

BenchmarkGPT-6 LunaGrok-3 mini
LMArena Coding14391379
DeepSWE66.6%—
FrontierCode42.4%—
Aider Polyglot—49.3%
LMArena WebDev1581—
SciCode54.6%—
WeirdML—42.6%
ALE-Bench1,577—

Agentic & Tool Use Not comparable

GPT-6 Luna: 33.3 (#54), Grok-3 mini: —

BenchmarkGPT-6 LunaGrok-3 mini
APEX-Agents44.3%—
GDP.pdf23%—

Reasoning GPT-6 Luna leads

GPT-6 Luna: 48.2 (#41), Grok-3 mini: 13.6 (#334)

BenchmarkGPT-6 LunaGrok-3 mini
ARC-AGI-259.3%0.4%
ARC-AGI-186.7%16.5%
LMArena Hard Prompts14111375
Epoch Capabilities Index156.28140.35
Kagi LLM Benchmark—61.3%
NYT Connections (extended)68.7%—
CritPt19.4%—
Chess Puzzles31%—
Mystery Game Puzzles7%—
DTBench90.1%—
LMCA44.5%—

Math GPT-6 Luna leads

GPT-6 Luna: 76.1 (#15), Grok-3 mini: 42.1 (#85)

BenchmarkGPT-6 LunaGrok-3 mini
OTIS Mock AIME 2024-202598.9%77.8%
LMArena Math14161386
FrontierMath (Tiers 1-3)78.9%—
FrontierMath Tier 456.1%—
ProofBench64%—
Omni-MATH—31.8%
MATH Level 5—90.9%
FrontierMath (Feb 2025 set)—5.9%

Knowledge GPT-6 Luna leads

GPT-6 Luna: 57.0 (#41), Grok-3 mini: 46.4 (#81)

BenchmarkGPT-6 LunaGrok-3 mini
GPQA Diamond90.5%76.3%
LMArena Expert14441395
SimpleQA Verified41.4%—
MMLU-Pro—79.9%
Confabulations—10.8%
GPQA (HELM)—67.5%

Multimodal Not comparable

GPT-6 Luna: 42.4 (#30), Grok-3 mini: —

BenchmarkGPT-6 LunaGrok-3 mini
LMArena Vision1217—
Blueprint-Bench 231.2%—
Furniture Assembly44.2%—

Multilingual GPT-6 Luna leads

GPT-6 Luna: 50.5 (#117), Grok-3 mini: 48.1 (#145)

BenchmarkGPT-6 LunaGrok-3 mini
LMArena Non-English13861352
LMArena Chinese14331387
LMArena French14201357
LMArena German13691349
LMArena Japanese13691342
LMArena Korean13601335
LMArena Russian13941353
LMArena Spanish13931381

Instruction Following Grok-3 mini leads

GPT-6 Luna: 74.3 (#99), Grok-3 mini: 78.5 (#9)

BenchmarkGPT-6 LunaGrok-3 mini
LMArena Instruction Following14091357
IFEval—95.1%

Long Context GPT-6 Luna leads

GPT-6 Luna: 43.0 (#111), Grok-3 mini: 41.0 (#147)

BenchmarkGPT-6 LunaGrok-3 mini
LMArena Longer Query14091372
Fiction.LiveBench—66.7%

Writing & Preference GPT-6 Luna leads

GPT-6 Luna: 58.3 (#119), Grok-3 mini: 52.5 (#169)

BenchmarkGPT-6 LunaGrok-3 mini
LMArena Text13911370
LMArena Creative Writing13631342
LMArena Multi-Turn13961355
Short-Story Creative Writing—73.5%
WildBench—65.1%

Frequently asked questions

Is GPT-6 Luna better than Grok-3 mini?

GPT-6 Luna is the stronger model overall, scoring 53.3 to 41.2 on the Noometry Index.

Is GPT-6 Luna or Grok-3 mini better for coding?

GPT-6 Luna scores higher on coding benchmarks: 55.5 versus 40.8 in the Noometry coding category.

How many benchmarks do GPT-6 Luna and Grok-3 mini share?

22 benchmarks have published results for both models. GPT-6 Luna has 42 scored results on Noometry and Grok-3 mini has 35.

Related comparisons

Go deeper