Noometry

Model comparison

GPT-4 vs Grok 4.7

Grok 4.7 is the stronger model overall, scoring 46.6 to 28.9 on the Noometry Index.

Last verified . 13 shared benchmarks.

GPT-4 OpenAI

28.9

Rank #308 Confirmed

Grok 4.7 xAI

46.6

Rank #56 Confirmed

Summary

  • They share 13 benchmarks with published results for both. GPT-4 scores higher in 0 categories and Grok 4.7 in 8 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in writing & preference, where Grok 4.7 leads 70.1 to 35.0.
  • Grok 4.7 is cheaper at $2 / $6 per million input/output tokens, against $30 / $60 for GPT-4.
  • Grok 4.7 accepts more context: 500K tokens versus 8K.

Side by side

GPT-4Grok 4.7
ProviderOpenAIxAI
Noometry Index28.946.6
Released2023-03-142026-09-21
WeightsProprietaryProprietary
Context window8K500K
Max output8K500K
Input $ / M tokens$30$2
Output $ / M tokens$60$6
Results tracked3821

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

Category by category

Coding Grok 4.7 leads

GPT-4: 31.2 (#277), Grok 4.7: 55.0 (#23)

BenchmarkGPT-4Grok 4.7
LMArena Coding12541423
CursorBench—46.3%
LMArena WebDev—1636
FrontierSWE—29.5%
SciCode—57.4%
WeirdML12.4%—
BigCodeBench Instruct46%—
BigCodeBench Complete57.2%—
HumanEval+79.3%—

Agentic & Tool Use Not comparable

GPT-4: —, Grok 4.7: —

BenchmarkGPT-4Grok 4.7
METR Time Horizons36.1%—

Reasoning Grok 4.7 leads

GPT-4: 17.3 (#285), Grok 4.7: 40.1 (#49)

BenchmarkGPT-4Grok 4.7
LMArena Hard Prompts12411409
NYT Connections (extended)—76.8%
CritPt—17.7%
Chess Puzzles4%—
Mystery Game Puzzles12%—
DTBench62.7%—
LMCA17.1%—
BIG-Bench Hard75.1%—
Epoch Capabilities Index125.88—
ForecastBench57.8—
HellaSwag95.3%—
WinoGrande87.5%—

Math Grok 4.7 leads

GPT-4: 10.1 (#304), Grok 4.7: 41.1 (#73)

BenchmarkGPT-4Grok 4.7
LMArena Math12691393
OTIS Mock AIME 2024-20251.1%—
ProofBench—34%
MATH Level 523%—
GSM8K92%—

Knowledge Grok 4.7 leads

GPT-4: 18.4 (#277), Grok 4.7: 38.7 (#130)

BenchmarkGPT-4Grok 4.7
LMArena Expert12111413
GPQA Diamond35.7%—
MMLU86.4%—
TriviaQA84.8%—

Multimodal Not comparable

GPT-4: —, Grok 4.7: 28.8 (#107)

BenchmarkGPT-4Grok 4.7
Furniture Assembly—20.8%

Multilingual Grok 4.7 leads

GPT-4: 40.8 (#210), Grok 4.7: 51.2 (#108)

BenchmarkGPT-4Grok 4.7
LMArena Non-English12461392
LMArena Chinese12421476
LMArena Russian12511396
LMArena French1282—
LMArena German1251—
LMArena Japanese1209—
LMArena Korean1184—
LMArena Spanish1261—

Instruction Following Grok 4.7 leads

GPT-4: 65.5 (#217), Grok 4.7: 74.3 (#98)

BenchmarkGPT-4Grok 4.7
LMArena Instruction Following12411406

Long Context Grok 4.7 leads

GPT-4: 37.7 (#207), Grok 4.7: 43.2 (#97)

BenchmarkGPT-4Grok 4.7
LMArena Longer Query12441416

Writing & Preference Grok 4.7 leads

GPT-4: 35.0 (#263), Grok 4.7: 70.1 (#23)

BenchmarkGPT-4Grok 4.7
LMArena Text12631397
LMArena Creative Writing12441391
EQ-Bench Creative Writing7522007
LMArena Multi-Turn12571389

Frequently asked questions

Is GPT-4 better than Grok 4.7?

Grok 4.7 is the stronger model overall, scoring 46.6 to 28.9 on the Noometry Index.

Which is cheaper, GPT-4 or Grok 4.7?

Grok 4.7 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 4.7 better for coding?

Grok 4.7 scores higher on coding benchmarks: 55.0 versus 31.2 in the Noometry coding category.

Which has the bigger context window?

Grok 4.7 does, with 500K tokens against 8K.

How many benchmarks do GPT-4 and Grok 4.7 share?

13 benchmarks have published results for both models. GPT-4 has 38 scored results on Noometry and Grok 4.7 has 21.

Related comparisons

Go deeper