Noometry

Model comparison

GPT-6 Sol vs Grok-3 mini

GPT-6 Sol is the stronger model overall, scoring 61.8 to 41.2 on the Noometry Index.

Last verified . 22 shared benchmarks.

GPT-6 Sol OpenAI

61.8

Rank #12 Confirmed

Grok-3 mini xAI

41.2

Rank #141 Confirmed

Summary

  • They share 22 benchmarks with published results for both. GPT-6 Sol 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 Sol leads 74.0 to 13.6.
  • The biggest single-benchmark swing is ARC-AGI-2: 89.6% for GPT-6 Sol and 0.4% for Grok-3 mini.

Side by side

GPT-6 SolGrok-3 mini
ProviderOpenAIxAI
Noometry Index61.841.2
Released2026-09-222025-04-09
WeightsProprietaryProprietary
Context window1.05M—
Max output128K—
Input $ / M tokens$2—
Output $ / M tokens$10—
Results tracked4535

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

Category by category

Coding GPT-6 Sol leads

GPT-6 Sol: 60.1 (#11), Grok-3 mini: 40.8 (#131)

BenchmarkGPT-6 SolGrok-3 mini
LMArena Coding14471379
DeepSWE68.8%—
FrontierCode49.3%—
Aider Polyglot—49.3%
LMArena WebDev1688—
SciCode57.6%—
WeirdML—42.6%
ALE-Bench2,462—

Agentic & Tool Use Not comparable

GPT-6 Sol: 37.2 (#36), Grok-3 mini: —

BenchmarkGPT-6 SolGrok-3 mini
APEX-Agents54.3%—
GDP.pdf26.4%—
Vending-Bench 214,428—

Reasoning GPT-6 Sol leads

GPT-6 Sol: 74.0 (#9), Grok-3 mini: 13.6 (#334)

BenchmarkGPT-6 SolGrok-3 mini
ARC-AGI-289.6%0.4%
ARC-AGI-195.5%16.5%
LMArena Hard Prompts14181375
Epoch Capabilities Index162.72140.35
Kagi LLM Benchmark—61.3%
NYT Connections (extended)90.1%—
CritPt30.9%—
EBR-Bench53.3%—
Mystery Game Puzzles56%—
DTBench97.3%—
LMCA59.1%—

Math GPT-6 Sol leads

GPT-6 Sol: 87.2 (#7), Grok-3 mini: 42.1 (#85)

BenchmarkGPT-6 SolGrok-3 mini
OTIS Mock AIME 2024-2025100%77.8%
LMArena Math14021386
FrontierMath (Tiers 1-3)89.8%—
FrontierMath Tier 490%—
ProofBench83%—
Omni-MATH—31.8%
MATH Level 5—90.9%
FrontierMath (Feb 2025 set)—5.9%

Knowledge GPT-6 Sol leads

GPT-6 Sol: 64.8 (#15), Grok-3 mini: 46.4 (#81)

BenchmarkGPT-6 SolGrok-3 mini
GPQA Diamond94.3%76.3%
LMArena Expert14391395
SimpleQA Verified60.7%—
MMLU-Pro—79.9%
Confabulations—10.8%
Vectara Hallucination Rate6.5%—
GPQA (HELM)—67.5%

Multimodal Not comparable

GPT-6 Sol: 47.6 (#10), Grok-3 mini: —

BenchmarkGPT-6 SolGrok-3 mini
LMArena Vision1245—
Blueprint-Bench 236.9%—
Furniture Assembly58.3%—

Multilingual GPT-6 Sol leads

GPT-6 Sol: 50.5 (#118), Grok-3 mini: 48.1 (#145)

BenchmarkGPT-6 SolGrok-3 mini
LMArena Non-English13851352
LMArena Chinese14051387
LMArena French14101357
LMArena German13901349
LMArena Japanese13851342
LMArena Korean13411335
LMArena Russian14011353
LMArena Spanish13841381

Instruction Following Grok-3 mini leads

GPT-6 Sol: 74.5 (#94), Grok-3 mini: 78.5 (#9)

BenchmarkGPT-6 SolGrok-3 mini
LMArena Instruction Following14121357
IFEval—95.1%

Long Context GPT-6 Sol leads

GPT-6 Sol: 43.1 (#108), Grok-3 mini: 41.0 (#147)

BenchmarkGPT-6 SolGrok-3 mini
LMArena Longer Query14111372
Fiction.LiveBench—66.7%

Writing & Preference GPT-6 Sol leads

GPT-6 Sol: 71.9 (#18), Grok-3 mini: 52.5 (#169)

BenchmarkGPT-6 SolGrok-3 mini
LMArena Text13951370
LMArena Creative Writing13781342
LMArena Multi-Turn14121355
Short-Story Creative Writing—73.5%
EQ-Bench Creative Writing2125—
WildBench—65.1%

Frequently asked questions

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

GPT-6 Sol is the stronger model overall, scoring 61.8 to 41.2 on the Noometry Index.

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

GPT-6 Sol scores higher on coding benchmarks: 60.1 versus 40.8 in the Noometry coding category.

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

22 benchmarks have published results for both models. GPT-6 Sol has 45 scored results on Noometry and Grok-3 mini has 35.

Related comparisons

Go deeper