Noometry

Model comparison

GPT-4.5 vs Grok 4

Grok 4 is the stronger model overall, scoring 47.8 to 36.9 on the Noometry Index.

Last verified . 30 shared benchmarks.

GPT-4.5 OpenAI

36.9

Rank #200 Confirmed

Grok 4 xAI

47.8

Rank #49 Confirmed

Summary

  • They share 30 benchmarks with published results for both. GPT-4.5 scores higher in 2 categories and Grok 4 in 8 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Grok 4 leads 36.9 to 14.1.
  • The biggest single-benchmark swing is ARC-AGI-1: 10.3% for GPT-4.5 and 66.7% for Grok 4.

Side by side

GPT-4.5Grok 4
ProviderOpenAIxAI
Noometry Index36.947.8
Released2025-02-272025-07-09
WeightsProprietaryProprietary
Context window——
Max output——
Input $ / M tokens——
Output $ / M tokens——
Results tracked4248

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

Category by category

Coding Grok 4 leads

GPT-4.5: 41.8 (#102), Grok 4: 49.9 (#44)

BenchmarkGPT-4.5Grok 4
Aider Polyglot44.9%79.6%
WeirdML39.4%45.7%
LMArena Coding13971408
LiveBench Coding75.2%—

Agentic & Tool Use Grok 4 leads

GPT-4.5: 27.6 (#92), Grok 4: 32.1 (#62)

BenchmarkGPT-4.5Grok 4
Cybench17.5%43%
Terminal-Bench—27.2%
Berkeley Function Calling Leaderboard—63%
GDPval—21.1%
DeepResearch Bench—47.3%
BALROG—43.6%
LMArena Search—1142
METR Time Horizons—66.6%

Reasoning Grok 4 leads

GPT-4.5: 14.1 (#320), Grok 4: 36.9 (#59)

BenchmarkGPT-4.5Grok 4
ARC-AGI-20.8%16%
SimpleBench34.5%60.5%
ARC-AGI-110.3%66.7%
LMArena Hard Prompts14041409
Epoch Capabilities Index136.74146.46
ForecastBench61.760.9
Kagi LLM Benchmark—73.6%
Chess Puzzles—28%
EnigmaEval3.2%—
LiveBench Reasoning71.1%—
LiveBench Data Analysis64.3%—
LiveBench69%—

Math Grok 4 leads

GPT-4.5: 31.0 (#200), Grok 4: 46.5 (#58)

BenchmarkGPT-4.5Grok 4
OTIS Mock AIME 2024-202537.8%84%
LMArena Math14121422
Omni-MATH—60.3%
LiveBench Math69.3%—
MATH Level 578.6%—
FrontierMath (Feb 2025 set)—19.7%
FrontierMath Tier 4 (v1)—2.1%

Knowledge Grok 4 leads

GPT-4.5: 32.4 (#205), Grok 4: 53.7 (#50)

BenchmarkGPT-4.5Grok 4
GPQA Diamond68.7%87%
Confabulations13.6%12.4%
LMArena Expert13941417
Humanity's Last Exam5.4%—
MMLU-Pro—85.1%
GPQA (HELM)—72.7%

Multimodal GPT-4.5 leads

GPT-4.5: 37.0 (#68), Grok 4: 33.1 (#89)

BenchmarkGPT-4.5Grok 4
LMArena Vision11951211
GeoBench—45%
VPCT45%—

Multilingual Too close to call

GPT-4.5: 52.7 (#78), Grok 4: 52.0 (#98)

BenchmarkGPT-4.5Grok 4
LMArena Non-English14131403
LMArena Chinese14211428
LMArena French14171418
LMArena German14571429
LMArena Japanese14161396
LMArena Korean13921376
LMArena Russian14191409
LMArena Spanish—1419

Instruction Following Grok 4 leads

GPT-4.5: 72.8 (#129), Grok 4: 79.4 (#4)

BenchmarkGPT-4.5Grok 4
LMArena Instruction Following14041387
LiveBench Instruction Following72.3%—
IFEval—94.9%

Long Context Grok 4 leads

GPT-4.5: 40.4 (#150), Grok 4: 63.1 (#4)

BenchmarkGPT-4.5Grok 4
Fiction.LiveBench63.9%94.4%
LMArena Longer Query14061409

Writing & Preference Grok 4 leads

GPT-4.5: 57.1 (#129), Grok 4: 58.7 (#111)

BenchmarkGPT-4.5Grok 4
LMArena Text14171412
LMArena Creative Writing13941397
Short-Story Creative Writing75.6%76.9%
LMArena Multi-Turn14441416
EQ-Bench Creative Writing1258—
WildBench—79.7%
LiveBench Language61.5%—

Frequently asked questions

Is GPT-4.5 better than Grok 4?

Grok 4 is the stronger model overall, scoring 47.8 to 36.9 on the Noometry Index.

Is GPT-4.5 or Grok 4 better for coding?

Grok 4 scores higher on coding benchmarks: 49.9 versus 41.8 in the Noometry coding category.

How many benchmarks do GPT-4.5 and Grok 4 share?

30 benchmarks have published results for both models. GPT-4.5 has 42 scored results on Noometry and Grok 4 has 48.

Related comparisons

Go deeper