Noometry

Model comparison

GPT-6.1 Sol vs Grok-3 mini

GPT-6.1 Sol is the stronger model overall, scoring 65.6 to 41.2 on the Noometry Index.

Last verified . 17 shared benchmarks.

GPT-6.1 Sol OpenAI

65.6

Rank #6 Confirmed

Grok-3 mini xAI

41.2

Rank #141 Confirmed

Summary

  • They share 17 benchmarks with published results for both. GPT-6.1 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-6.1 Sol leads 81.9 to 13.6.
  • The biggest single-benchmark swing is ARC-AGI-2: 94.2% for GPT-6.1 Sol and 0.4% for Grok-3 mini.

Side by side

GPT-6.1 SolGrok-3 mini
ProviderOpenAIxAI
Noometry Index65.641.2
Released2026-09-292025-04-09
WeightsProprietaryProprietary
Context window1.05M—
Max output128K—
Input $ / M tokens$2—
Output $ / M tokens$10—
Results tracked3435

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

Category by category

Coding GPT-6.1 Sol leads

GPT-6.1 Sol: 63.2 (#8), Grok-3 mini: 40.8 (#131)

BenchmarkGPT-6.1 SolGrok-3 mini
LMArena Coding14871379
DeepSWE75.2%—
FrontierCode50.2%—
Aider Polyglot—49.3%
LMArena WebDev1755—
SciCode55.8%—
WeirdML—42.6%

Agentic & Tool Use Not comparable

GPT-6.1 Sol: 39.6 (#26), Grok-3 mini: —

BenchmarkGPT-6.1 SolGrok-3 mini
APEX-Agents60%—
GDP.pdf32%—

Reasoning GPT-6.1 Sol leads

GPT-6.1 Sol: 81.9 (#2), Grok-3 mini: 13.6 (#334)

BenchmarkGPT-6.1 SolGrok-3 mini
ARC-AGI-294.2%0.4%
ARC-AGI-198.5%16.5%
LMArena Hard Prompts14661375
Epoch Capabilities Index166.09140.35
Kagi LLM Benchmark—61.3%
NYT Connections (extended)95.5%—
CritPt31.7%—
Chess Puzzles61%—
EBR-Bench54.3%—
Mystery Game Puzzles80%—

Math GPT-6.1 Sol leads

GPT-6.1 Sol: 93.7 (#1), Grok-3 mini: 42.1 (#85)

BenchmarkGPT-6.1 SolGrok-3 mini
OTIS Mock AIME 2024-2025100%77.8%
LMArena Math14641386
FrontierMath (Tiers 1-3)93.7%—
FrontierMath Tier 4100%—
ProofBench99%—
Omni-MATH—31.8%
MATH Level 5—90.9%
FrontierMath (Feb 2025 set)—5.9%

Knowledge GPT-6.1 Sol leads

GPT-6.1 Sol: 71.8 (#4), Grok-3 mini: 46.4 (#81)

BenchmarkGPT-6.1 SolGrok-3 mini
GPQA Diamond95.4%76.3%
LMArena Expert15021395
SimpleQA Verified73.9%—
MMLU-Pro—79.9%
Confabulations—10.8%
GPQA (HELM)—67.5%

Multimodal Not comparable

GPT-6.1 Sol: 52.7 (#5), Grok-3 mini: —

BenchmarkGPT-6.1 SolGrok-3 mini
LMArena Vision1288—
Furniture Assembly80%—

Multilingual GPT-6.1 Sol leads

GPT-6.1 Sol: 54.3 (#46), Grok-3 mini: 48.1 (#145)

BenchmarkGPT-6.1 SolGrok-3 mini
LMArena Non-English14381352
LMArena Chinese14771387
LMArena Russian14551353
LMArena French—1357
LMArena German—1349
LMArena Japanese—1342
LMArena Korean—1335
LMArena Spanish—1381

Instruction Following Grok-3 mini leads

GPT-6.1 Sol: 77.0 (#29), Grok-3 mini: 78.5 (#9)

BenchmarkGPT-6.1 SolGrok-3 mini
LMArena Instruction Following14681357
IFEval—95.1%

Long Context GPT-6.1 Sol leads

GPT-6.1 Sol: 44.9 (#54), Grok-3 mini: 41.0 (#147)

BenchmarkGPT-6.1 SolGrok-3 mini
LMArena Longer Query14651372
Fiction.LiveBench—66.7%

Writing & Preference GPT-6.1 Sol leads

GPT-6.1 Sol: 63.6 (#63), Grok-3 mini: 52.5 (#169)

BenchmarkGPT-6.1 SolGrok-3 mini
LMArena Text14471370
LMArena Creative Writing14321342
LMArena Multi-Turn14491355
Short-Story Creative Writing—73.5%
WildBench—65.1%

Frequently asked questions

Is GPT-6.1 Sol better than Grok-3 mini?

GPT-6.1 Sol is the stronger model overall, scoring 65.6 to 41.2 on the Noometry Index.

Is GPT-6.1 Sol or Grok-3 mini better for coding?

GPT-6.1 Sol scores higher on coding benchmarks: 63.2 versus 40.8 in the Noometry coding category.

How many benchmarks do GPT-6.1 Sol and Grok-3 mini share?

17 benchmarks have published results for both models. GPT-6.1 Sol has 34 scored results on Noometry and Grok-3 mini has 35.

Related comparisons

Go deeper