Noometry

Model comparison

GPT-4.5 vs Grok 4.6

Grok 4.6 is the stronger model overall, scoring 56.9 to 37.2 on the Noometry Index.

Last verified . 24 shared benchmarks.

GPT-4.5 OpenAI

37.2

Rank #208 Confirmed

Grok 4.6 xAI

56.9

Rank #21 Confirmed

Summary

  • They share 24 benchmarks with published results for both. GPT-4.5 scores higher in 0 categories and Grok 4.6 in 10 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Grok 4.6 leads 61.4 to 13.9.
  • The biggest single-benchmark swing is ARC-AGI-1: 10.3% for GPT-4.5 and 87.5% for Grok 4.6.

Side by side

GPT-4.5Grok 4.6
ProviderOpenAIxAI
Noometry Index37.256.9
Released2025-02-272026-08-12
WeightsProprietaryProprietary
Context window—500K
Max output—500K
Input $ / M tokens—$2
Output $ / M tokens—$6
Results tracked4249

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

Category by category

Coding Grok 4.6 leads

GPT-4.5: 42.2 (#109), Grok 4.6: 58.5 (#16)

BenchmarkGPT-4.5Grok 4.6
WeirdML39.4%67.3%
LMArena Coding13961465
DeepSWE—67.5%
FrontierCode—48%
Aider Polyglot44.9%—
CursorBench—41.4%
LMArena WebDev—1617
FrontierSWE—25.3%
SciCode—56.5%
LiveBench Coding75.2%—
ALE-Bench—1,508

Agentic & Tool Use Grok 4.6 leads

GPT-4.5: 27.9 (#97), Grok 4.6: 39.4 (#27)

BenchmarkGPT-4.5Grok 4.6
APEX-Agents—65.3%
Cybench17.5%—
GDP.pdf—17.2%
Vending-Bench 2—9,047

Reasoning Grok 4.6 leads

GPT-4.5: 13.9 (#330), Grok 4.6: 61.4 (#20)

BenchmarkGPT-4.5Grok 4.6
ARC-AGI-20.8%67.1%
SimpleBench34.5%75.9%
ARC-AGI-110.3%87.5%
LMArena Hard Prompts14031447
Epoch Capabilities Index136.74156.44
NYT Connections (extended)—80%
CritPt—19.7%
Chess Puzzles—40%
EnigmaEval3.2%—
EBR-Bench—30.5%
LiveBench Reasoning71.1%—
Mystery Game Puzzles—34%
DTBench—97.3%
LiveBench Data Analysis64.3%—
LMCA—48.5%
ForecastBench61.7—
LiveBench69%—

Math Grok 4.6 leads

GPT-4.5: 32.6 (#211), Grok 4.6: 67.0 (#24)

BenchmarkGPT-4.5Grok 4.6
OTIS Mock AIME 2024-202537.8%99.2%
LMArena Math14121423
FrontierMath (Tiers 1-3)—66%
FrontierMath Tier 4—31.7%
ProofBench—51%
LiveBench Math69.3%—
MATH Level 578.6%—

Knowledge Grok 4.6 leads

GPT-4.5: 32.5 (#211), Grok 4.6: 63.3 (#20)

BenchmarkGPT-4.5Grok 4.6
GPQA Diamond68.7%94%
LMArena Expert13941467
Humanity's Last Exam5.4%—
SimpleQA Verified—49.3%
Confabulations13.6%—

Multimodal Grok 4.6 leads

GPT-4.5: 37.6 (#71), Grok 4.6: 43.6 (#23)

BenchmarkGPT-4.5Grok 4.6
LMArena Vision11951263
VPCT45%—
Blueprint-Bench 2—33.2%
Furniture Assembly—40%
LMArena Document—1452

Multilingual Too close to call

GPT-4.5: 52.5 (#83), Grok 4.6: 53.0 (#74)

BenchmarkGPT-4.5Grok 4.6
LMArena Non-English14131420
LMArena Chinese14211480
LMArena French14181461
LMArena German14571431
LMArena Japanese14161376
LMArena Korean13921397
LMArena Russian14191422
LMArena Spanish—1404

Instruction Following Grok 4.6 leads

GPT-4.5: 72.6 (#134), Grok 4.6: 75.4 (#63)

BenchmarkGPT-4.5Grok 4.6
LMArena Instruction Following14041431
LiveBench Instruction Following72.3%—

Long Context Grok 4.6 leads

GPT-4.5: 40.4 (#155), Grok 4.6: 44.5 (#66)

BenchmarkGPT-4.5Grok 4.6
LMArena Longer Query14061454
Fiction.LiveBench63.9%—

Writing & Preference Grok 4.6 leads

GPT-4.5: 56.9 (#134), Grok 4.6: 62.3 (#80)

BenchmarkGPT-4.5Grok 4.6
LMArena Text14171428
LMArena Creative Writing13941428
LMArena Multi-Turn14441425
Short-Story Creative Writing75.6%—
EQ-Bench Creative Writing1258—
LiveBench Language61.5%—

Frequently asked questions

Is GPT-4.5 better than Grok 4.6?

Grok 4.6 is the stronger model overall, scoring 56.9 to 37.2 on the Noometry Index.

Is GPT-4.5 or Grok 4.6 better for coding?

Grok 4.6 scores higher on coding benchmarks: 58.5 versus 42.2 in the Noometry coding category.

How many benchmarks do GPT-4.5 and Grok 4.6 share?

24 benchmarks have published results for both models. GPT-4.5 has 42 scored results on Noometry and Grok 4.6 has 49.

Related comparisons

Go deeper