Noometry

Model comparison

GPT-4 vs Grok 4

Grok 4 is the stronger model overall, scoring 48.1 to 29.1 on the Noometry Index.

Last verified . 24 shared benchmarks.

GPT-4 OpenAI

29.1

Rank #316 Confirmed

Grok 4 xAI

48.1

Rank #56 Confirmed

Summary

  • They share 24 benchmarks with published results for both. GPT-4 scores higher in 0 categories and Grok 4 in 8 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in math, where Grok 4 leads 48.4 to 10.8.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 1.1% for GPT-4 and 84% for Grok 4.

Side by side

GPT-4Grok 4
ProviderOpenAIxAI
Noometry Index29.148.1
Released2023-03-142025-07-09
WeightsProprietaryProprietary
Context window8K—
Max output8K—
Input $ / M tokens$30—
Output $ / M tokens$60—
Results tracked3848

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

Category by category

Coding Grok 4 leads

GPT-4: 31.6 (#283), Grok 4: 50.3 (#46)

BenchmarkGPT-4Grok 4
WeirdML12.4%45.7%
LMArena Coding12541408
Aider Polyglot—79.6%
BigCodeBench Instruct46%—
BigCodeBench Complete57.2%—
HumanEval+79.3%—

Agentic & Tool Use Not comparable

GPT-4: —, Grok 4: 32.3 (#68)

BenchmarkGPT-4Grok 4
METR Time Horizons36.1%66.6%
Terminal-Bench—27.2%
Berkeley Function Calling Leaderboard—63%
GDPval—21.1%
Cybench—43%
DeepResearch Bench—47.3%
BALROG—43.6%
LMArena Search—1142

Reasoning Grok 4 leads

GPT-4: 17.8 (#289), Grok 4: 36.7 (#65)

BenchmarkGPT-4Grok 4
Chess Puzzles4%28%
LMArena Hard Prompts12411409
Epoch Capabilities Index125.89146.44
ForecastBench57.860.9
ARC-AGI-2—16%
SimpleBench—60.5%
Kagi LLM Benchmark—73.6%
ARC-AGI-1—66.7%
Mystery Game Puzzles12%—
DTBench62.7%—
LMCA17.1%—
BIG-Bench Hard75.1%—
HellaSwag95.3%—
WinoGrande87.5%—

Math Grok 4 leads

GPT-4: 10.8 (#309), Grok 4: 48.4 (#64)

BenchmarkGPT-4Grok 4
OTIS Mock AIME 2024-20251.1%84%
LMArena Math12691422
Omni-MATH—60.3%
MATH Level 523%—
FrontierMath (Feb 2025 set)—19.7%
FrontierMath Tier 4 (v1)—2.1%
GSM8K92%—

Knowledge Grok 4 leads

GPT-4: 18.4 (#282), Grok 4: 53.8 (#55)

BenchmarkGPT-4Grok 4
GPQA Diamond35.7%87%
LMArena Expert12111415
MMLU-Pro—85.1%
Confabulations—12.4%
GPQA (HELM)—72.7%
MMLU86.4%—
TriviaQA84.8%—

Multimodal Not comparable

GPT-4: —, Grok 4: 33.7 (#94)

BenchmarkGPT-4Grok 4
LMArena Vision—1210
GeoBench—45%

Multilingual Grok 4 leads

GPT-4: 40.6 (#215), Grok 4: 51.8 (#103)

BenchmarkGPT-4Grok 4
LMArena Non-English12461403
LMArena Chinese12421427
LMArena French12831418
LMArena German12511429
LMArena Japanese12091394
LMArena Korean11841377
LMArena Russian12511410
LMArena Spanish12611420

Instruction Following Grok 4 leads

GPT-4: 65.3 (#222), Grok 4: 79.2 (#5)

BenchmarkGPT-4Grok 4
LMArena Instruction Following12411387
IFEval—94.9%

Long Context Grok 4 leads

GPT-4: 37.7 (#212), Grok 4: 63.1 (#4)

BenchmarkGPT-4Grok 4
LMArena Longer Query12441409
Fiction.LiveBench—94.4%

Writing & Preference Grok 4 leads

GPT-4: 34.9 (#268), Grok 4: 58.5 (#116)

BenchmarkGPT-4Grok 4
LMArena Text12631411
LMArena Creative Writing12441397
LMArena Multi-Turn12571416
Short-Story Creative Writing—76.9%
EQ-Bench Creative Writing752—
WildBench—79.7%

Frequently asked questions

Is GPT-4 better than Grok 4?

Grok 4 is the stronger model overall, scoring 48.1 to 29.1 on the Noometry Index.

Is GPT-4 or Grok 4 better for coding?

Grok 4 scores higher on coding benchmarks: 50.3 versus 31.6 in the Noometry coding category.

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

24 benchmarks have published results for both models. GPT-4 has 38 scored results on Noometry and Grok 4 has 48.

Related comparisons

Go deeper