Noometry

Model comparison

GPT-4 vs Grok 4.6

Grok 4.6 is the stronger model overall, scoring 56.9 to 29.1 on the Noometry Index.

Last verified . 25 shared benchmarks.

GPT-4 OpenAI

29.1

Rank #316 Confirmed

Grok 4.6 xAI

56.9

Rank #21 Confirmed

Summary

  • They share 25 benchmarks with published results for both. GPT-4 scores higher in 0 categories and Grok 4.6 in 8 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in math, where Grok 4.6 leads 67.0 to 10.8.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 1.1% for GPT-4 and 99.2% for Grok 4.6.
  • Grok 4.6 is cheaper at $2 / $6 per million input/output tokens, against $30 / $60 for GPT-4.
  • Grok 4.6 accepts more context: 500K tokens versus 8K.

Side by side

GPT-4Grok 4.6
ProviderOpenAIxAI
Noometry Index29.156.9
Released2023-03-142026-08-12
WeightsProprietaryProprietary
Context window8K500K
Max output8K500K
Input $ / M tokens$30$2
Output $ / M tokens$60$6
Results tracked3849

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

Category by category

Coding Grok 4.6 leads

GPT-4: 31.6 (#283), Grok 4.6: 58.5 (#16)

BenchmarkGPT-4Grok 4.6
WeirdML12.4%67.3%
LMArena Coding12541465
DeepSWE—67.5%
FrontierCode—48%
CursorBench—41.4%
LMArena WebDev—1617
FrontierSWE—25.3%
SciCode—56.5%
BigCodeBench Instruct46%—
BigCodeBench Complete57.2%—
ALE-Bench—1,508
HumanEval+79.3%—

Agentic & Tool Use Not comparable

GPT-4: —, Grok 4.6: 39.4 (#27)

BenchmarkGPT-4Grok 4.6
APEX-Agents—65.3%
GDP.pdf—17.2%
METR Time Horizons36.1%—
Vending-Bench 2—9,047

Reasoning Grok 4.6 leads

GPT-4: 17.8 (#289), Grok 4.6: 61.4 (#20)

BenchmarkGPT-4Grok 4.6
Chess Puzzles4%40%
LMArena Hard Prompts12411447
Mystery Game Puzzles12%34%
DTBench62.7%97.3%
LMCA17.1%48.5%
Epoch Capabilities Index125.89156.44
ARC-AGI-2—67.1%
SimpleBench—75.9%
NYT Connections (extended)—80%
ARC-AGI-1—87.5%
CritPt—19.7%
EBR-Bench—30.5%
BIG-Bench Hard75.1%—
ForecastBench57.8—
HellaSwag95.3%—
WinoGrande87.5%—

Math Grok 4.6 leads

GPT-4: 10.8 (#309), Grok 4.6: 67.0 (#24)

BenchmarkGPT-4Grok 4.6
OTIS Mock AIME 2024-20251.1%99.2%
LMArena Math12691423
FrontierMath (Tiers 1-3)—66%
FrontierMath Tier 4—31.7%
ProofBench—51%
MATH Level 523%—
GSM8K92%—

Knowledge Grok 4.6 leads

GPT-4: 18.4 (#282), Grok 4.6: 63.3 (#20)

BenchmarkGPT-4Grok 4.6
GPQA Diamond35.7%94%
LMArena Expert12111467
SimpleQA Verified—49.3%
MMLU86.4%—
TriviaQA84.8%—

Multimodal Not comparable

GPT-4: —, Grok 4.6: 43.6 (#23)

BenchmarkGPT-4Grok 4.6
LMArena Vision—1263
Blueprint-Bench 2—33.2%
Furniture Assembly—40%
LMArena Document—1452

Multilingual Grok 4.6 leads

GPT-4: 40.6 (#215), Grok 4.6: 53.0 (#74)

BenchmarkGPT-4Grok 4.6
LMArena Non-English12461420
LMArena Chinese12421480
LMArena French12831461
LMArena German12511431
LMArena Japanese12091376
LMArena Korean11841397
LMArena Russian12511422
LMArena Spanish12611404

Instruction Following Grok 4.6 leads

GPT-4: 65.3 (#222), Grok 4.6: 75.4 (#63)

BenchmarkGPT-4Grok 4.6
LMArena Instruction Following12411431

Long Context Grok 4.6 leads

GPT-4: 37.7 (#212), Grok 4.6: 44.5 (#66)

BenchmarkGPT-4Grok 4.6
LMArena Longer Query12441454

Writing & Preference Grok 4.6 leads

GPT-4: 34.9 (#268), Grok 4.6: 62.3 (#80)

BenchmarkGPT-4Grok 4.6
LMArena Text12631428
LMArena Creative Writing12441428
LMArena Multi-Turn12571425
EQ-Bench Creative Writing752—

Frequently asked questions

Is GPT-4 better than Grok 4.6?

Grok 4.6 is the stronger model overall, scoring 56.9 to 29.1 on the Noometry Index.

Which is cheaper, GPT-4 or Grok 4.6?

Grok 4.6 is cheaper. It lists at $2 per million input tokens and $6 per million output tokens; GPT-4 lists at $30 and $60.

Is GPT-4 or Grok 4.6 better for coding?

Grok 4.6 scores higher on coding benchmarks: 58.5 versus 31.6 in the Noometry coding category.

Which has the bigger context window?

Grok 4.6 does, with 500K tokens against 8K.

How many benchmarks do GPT-4 and Grok 4.6 share?

25 benchmarks have published results for both models. GPT-4 has 38 scored results on Noometry and Grok 4.6 has 49.

Related comparisons

Go deeper