Noometry

Model comparison

GPT-6.1 Sol vs Grok 4

GPT-6.1 Sol is the stronger model overall, scoring 65.6 to 48.1 on the Noometry Index.

Last verified . 19 shared benchmarks.

GPT-6.1 Sol OpenAI

65.6

Rank #6 Confirmed

Grok 4 xAI

48.1

Rank #56 Confirmed

Summary

  • They share 19 benchmarks with published results for both. GPT-6.1 Sol scores higher in 8 categories and Grok 4 in 2 categories; 10 gaps are clear of the uncertainty.
  • The widest gap is in math, where GPT-6.1 Sol leads 93.7 to 48.4.
  • The biggest single-benchmark swing is ARC-AGI-2: 94.2% for GPT-6.1 Sol and 16% for Grok 4.

Side by side

GPT-6.1 SolGrok 4
ProviderOpenAIxAI
Noometry Index65.648.1
Released2026-09-292025-07-09
WeightsProprietaryProprietary
Context window1.05M—
Max output128K—
Input $ / M tokens$2—
Output $ / M tokens$10—
Results tracked3448

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 4: 50.3 (#46)

BenchmarkGPT-6.1 SolGrok 4
LMArena Coding14871408
DeepSWE75.2%—
FrontierCode50.2%—
Aider Polyglot—79.6%
LMArena WebDev1755—
SciCode55.8%—
WeirdML—45.7%

Agentic & Tool Use GPT-6.1 Sol leads

GPT-6.1 Sol: 39.6 (#26), Grok 4: 32.3 (#68)

BenchmarkGPT-6.1 SolGrok 4
Terminal-Bench—27.2%
APEX-Agents60%—
Berkeley Function Calling Leaderboard—63%
GDPval—21.1%
Cybench—43%
DeepResearch Bench—47.3%
BALROG—43.6%
GDP.pdf32%—
LMArena Search—1142
METR Time Horizons—66.6%

Reasoning GPT-6.1 Sol leads

GPT-6.1 Sol: 81.9 (#2), Grok 4: 36.7 (#65)

BenchmarkGPT-6.1 SolGrok 4
ARC-AGI-294.2%16%
ARC-AGI-198.5%66.7%
Chess Puzzles61%28%
LMArena Hard Prompts14661409
Epoch Capabilities Index166.09146.44
SimpleBench—60.5%
Kagi LLM Benchmark—73.6%
NYT Connections (extended)95.5%—
CritPt31.7%—
EBR-Bench54.3%—
Mystery Game Puzzles80%—
ForecastBench—60.9

Math GPT-6.1 Sol leads

GPT-6.1 Sol: 93.7 (#1), Grok 4: 48.4 (#64)

BenchmarkGPT-6.1 SolGrok 4
OTIS Mock AIME 2024-2025100%84%
LMArena Math14641422
FrontierMath (Tiers 1-3)93.7%—
FrontierMath Tier 4100%—
ProofBench99%—
Omni-MATH—60.3%
FrontierMath (Feb 2025 set)—19.7%
FrontierMath Tier 4 (v1)—2.1%

Knowledge GPT-6.1 Sol leads

GPT-6.1 Sol: 71.8 (#4), Grok 4: 53.8 (#55)

BenchmarkGPT-6.1 SolGrok 4
GPQA Diamond95.4%87%
LMArena Expert15021415
SimpleQA Verified73.9%—
MMLU-Pro—85.1%
Confabulations—12.4%
GPQA (HELM)—72.7%

Multimodal GPT-6.1 Sol leads

GPT-6.1 Sol: 52.7 (#5), Grok 4: 33.7 (#94)

BenchmarkGPT-6.1 SolGrok 4
LMArena Vision12881210
GeoBench—45%
Furniture Assembly80%—

Multilingual GPT-6.1 Sol leads

GPT-6.1 Sol: 54.3 (#46), Grok 4: 51.8 (#103)

BenchmarkGPT-6.1 SolGrok 4
LMArena Non-English14381403
LMArena Chinese14771427
LMArena Russian14551410
LMArena French—1418
LMArena German—1429
LMArena Japanese—1394
LMArena Korean—1377
LMArena Spanish—1420

Instruction Following Grok 4 leads

GPT-6.1 Sol: 77.0 (#29), Grok 4: 79.2 (#5)

BenchmarkGPT-6.1 SolGrok 4
LMArena Instruction Following14681387
IFEval—94.9%

Long Context Grok 4 leads

GPT-6.1 Sol: 44.9 (#54), Grok 4: 63.1 (#4)

BenchmarkGPT-6.1 SolGrok 4
LMArena Longer Query14651409
Fiction.LiveBench—94.4%

Writing & Preference GPT-6.1 Sol leads

GPT-6.1 Sol: 63.6 (#63), Grok 4: 58.5 (#116)

BenchmarkGPT-6.1 SolGrok 4
LMArena Text14471411
LMArena Creative Writing14321397
LMArena Multi-Turn14491416
Short-Story Creative Writing—76.9%
WildBench—79.7%

Frequently asked questions

Is GPT-6.1 Sol better than Grok 4?

GPT-6.1 Sol is the stronger model overall, scoring 65.6 to 48.1 on the Noometry Index.

Is GPT-6.1 Sol or Grok 4 better for coding?

GPT-6.1 Sol scores higher on coding benchmarks: 63.2 versus 50.3 in the Noometry coding category.

How many benchmarks do GPT-6.1 Sol and Grok 4 share?

19 benchmarks have published results for both models. GPT-6.1 Sol has 34 scored results on Noometry and Grok 4 has 48.

Related comparisons

Go deeper