Noometry

Model comparison

GPT-6 Luna vs Grok 3

GPT-6 Luna is the stronger model overall, scoring 53.3 to 39.9 on the Noometry Index.

Last verified . 22 shared benchmarks.

GPT-6 Luna OpenAI

53.3

Rank #36 Confirmed

Grok 3 xAI

39.9

Rank #157 Confirmed

Summary

  • They share 22 benchmarks with published results for both. GPT-6 Luna scores higher in 7 categories and Grok 3 in 2 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in math, where GPT-6 Luna leads 76.1 to 38.0.
  • The biggest single-benchmark swing is ARC-AGI-1: 86.7% for GPT-6 Luna and 5.5% for Grok 3.

Side by side

GPT-6 LunaGrok 3
ProviderOpenAIxAI
Noometry Index53.339.9
Released2026-09-222025-04-09
WeightsProprietaryProprietary
Context window1.05M—
Max output128K—
Input $ / M tokens$0.10—
Output $ / M tokens$0.50—
Results tracked4240

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: 41.9 (#115)

BenchmarkGPT-6 LunaGrok 3
LMArena Coding14391432
DeepSWE66.6%—
FrontierCode42.4%—
Aider Polyglot—53.3%
LMArena WebDev1581—
SciCode54.6%—
WeirdML—37.2%
ALE-Bench1,577—

Agentic & Tool Use GPT-6 Luna leads

GPT-6 Luna: 33.3 (#54), Grok 3: 30.5 (#76)

BenchmarkGPT-6 LunaGrok 3
APEX-Agents44.3%—
BALROG—29.5%
GDP.pdf23%—

Reasoning GPT-6 Luna leads

GPT-6 Luna: 48.2 (#41), Grok 3: 13.7 (#333)

BenchmarkGPT-6 LunaGrok 3
ARC-AGI-259.3%0%
ARC-AGI-186.7%5.5%
LMArena Hard Prompts14111434
Epoch Capabilities Index156.28138.33
SimpleBench—36.1%
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: 38.0 (#145)

BenchmarkGPT-6 LunaGrok 3
OTIS Mock AIME 2024-202598.9%55.6%
LMArena Math14161391
FrontierMath (Tiers 1-3)78.9%—
FrontierMath Tier 456.1%—
ProofBench64%—
Omni-MATH—46.4%
MATH Level 5—88.7%
FrontierMath (Feb 2025 set)—3.8%
FrontierMath Tier 4 (v1)—0%

Knowledge GPT-6 Luna leads

GPT-6 Luna: 57.0 (#41), Grok 3: 46.2 (#82)

BenchmarkGPT-6 LunaGrok 3
GPQA Diamond90.5%75.8%
LMArena Expert14441421
SimpleQA Verified41.4%—
MMLU-Pro—78.8%
Confabulations—14.2%
Vectara Hallucination Rate—5.8%
GPQA (HELM)—65%

Multimodal Not comparable

GPT-6 Luna: 42.4 (#30), Grok 3: —

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

Multilingual Grok 3 leads

GPT-6 Luna: 50.5 (#117), Grok 3: 52.3 (#87)

BenchmarkGPT-6 LunaGrok 3
LMArena Non-English13861410
LMArena Chinese14331448
LMArena French14201460
LMArena German13691431
LMArena Japanese13691387
LMArena Korean13601373
LMArena Russian13941416
LMArena Spanish13931417

Instruction Following Too close to call

GPT-6 Luna: 74.3 (#99), Grok 3: 75.0 (#73)

BenchmarkGPT-6 LunaGrok 3
LMArena Instruction Following14091409
IFEval—88.4%

Long Context GPT-6 Luna leads

GPT-6 Luna: 43.0 (#111), Grok 3: 38.7 (#192)

BenchmarkGPT-6 LunaGrok 3
LMArena Longer Query14091439
Fiction.LiveBench—58.3%

Writing & Preference GPT-6 Luna leads

GPT-6 Luna: 58.3 (#119), Grok 3: 55.8 (#141)

BenchmarkGPT-6 LunaGrok 3
LMArena Text13911426
LMArena Creative Writing13631414
LMArena Multi-Turn13961425
Short-Story Creative Writing—76.4%
EQ-Bench Creative Writing—1186
WildBench—84.9%

Frequently asked questions

Is GPT-6 Luna better than Grok 3?

GPT-6 Luna is the stronger model overall, scoring 53.3 to 39.9 on the Noometry Index.

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

GPT-6 Luna scores higher on coding benchmarks: 55.5 versus 41.9 in the Noometry coding category.

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

22 benchmarks have published results for both models. GPT-6 Luna has 42 scored results on Noometry and Grok 3 has 40.

Related comparisons

Go deeper