Noometry

Model comparison

Grok 4 vs Grok 4.7

Grok 4.7 is the stronger model overall, scoring 53.1 to 48.1 on the Noometry Index.

Last verified . 19 shared benchmarks.

Grok 4 xAI

48.1

Rank #56 Confirmed

Grok 4.7 xAI

53.1

Rank #37 Confirmed

Summary

  • They share 19 benchmarks with published results for both. Grok 4 scores higher in 3 categories and Grok 4.7 in 7 categories; 10 gaps are clear of the uncertainty.
  • The widest gap is in long context, where Grok 4 leads 63.1 to 43.1.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 84% for Grok 4 and 98.1% for Grok 4.7.

Side by side

Grok 4Grok 4.7
ProviderxAIxAI
Noometry Index48.153.1
Released2025-07-092026-09-21
WeightsProprietaryProprietary
Context window—500K
Max output—500K
Input $ / M tokens—$2
Output $ / M tokens—$6
Results tracked4839

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

Category by category

Coding Grok 4.7 leads

Grok 4: 50.3 (#46), Grok 4.7: 58.0 (#18)

BenchmarkGrok 4Grok 4.7
LMArena Coding14081427
FrontierCode—47.6%
Aider Polyglot79.6%—
CursorBench—46.3%
LMArena WebDev—1639
FrontierSWE—29.5%
SciCode—57.8%
WeirdML45.7%—

Agentic & Tool Use Grok 4.7 leads

Grok 4: 32.3 (#68), Grok 4.7: 36.7 (#37)

BenchmarkGrok 4Grok 4.7
Terminal-Bench27.2%—
APEX-Agents—54.6%
Berkeley Function Calling Leaderboard63%—
GDPval21.1%—
Cybench43%—
DeepResearch Bench47.3%—
BALROG43.6%—
GDP.pdf—22.8%
LMArena Search1142—
METR Time Horizons66.6%—
Vending-Bench 2—10,537

Reasoning Grok 4.7 leads

Grok 4: 36.7 (#65), Grok 4.7: 49.1 (#40)

BenchmarkGrok 4Grok 4.7
Chess Puzzles28%38%
LMArena Hard Prompts14091413
Epoch Capabilities Index146.44153.53
ARC-AGI-216%—
SimpleBench60.5%—
Kagi LLM Benchmark73.6%—
NYT Connections (extended)—76.8%
ARC-AGI-166.7%—
CritPt—18%
Mystery Game Puzzles—29%
DTBench—96%
LMCA—49.4%
ForecastBench60.9—

Math Grok 4.7 leads

Grok 4: 48.4 (#64), Grok 4.7: 57.8 (#39)

BenchmarkGrok 4Grok 4.7
OTIS Mock AIME 2024-202584%98.1%
LMArena Math14221407
FrontierMath (Tiers 1-3)—53%
FrontierMath Tier 4—17.1%
ProofBench—34%
Omni-MATH60.3%—
FrontierMath (Feb 2025 set)19.7%—
FrontierMath Tier 4 (v1)2.1%—

Knowledge Grok 4.7 leads

Grok 4: 53.8 (#55), Grok 4.7: 62.8 (#22)

BenchmarkGrok 4Grok 4.7
GPQA Diamond87%92.7%
LMArena Expert14151422
SimpleQA Verified—56%
MMLU-Pro85.1%—
Confabulations12.4%—
GPQA (HELM)72.7%—

Multimodal Grok 4.7 leads

Grok 4: 33.7 (#94), Grok 4.7: 35.5 (#87)

BenchmarkGrok 4Grok 4.7
LMArena Vision12101228
GeoBench45%—
Blueprint-Bench 2—32.5%
Furniture Assembly—20.8%

Multilingual Grok 4 leads

Grok 4: 51.8 (#103), Grok 4.7: 50.8 (#116)

BenchmarkGrok 4Grok 4.7
LMArena Non-English14031389
LMArena Chinese14271455
LMArena French14181455
LMArena Russian14101397
LMArena Spanish14201400
LMArena German1429—
LMArena Japanese1394—
LMArena Korean1377—

Instruction Following Grok 4 leads

Grok 4: 79.2 (#5), Grok 4.7: 74.1 (#105)

BenchmarkGrok 4Grok 4.7
LMArena Instruction Following13871404
IFEval94.9%—

Long Context Grok 4 leads

Grok 4: 63.1 (#4), Grok 4.7: 43.1 (#104)

BenchmarkGrok 4Grok 4.7
LMArena Longer Query14091413
Fiction.LiveBench94.4%—

Writing & Preference Grok 4.7 leads

Grok 4: 58.5 (#116), Grok 4.7: 70.0 (#24)

BenchmarkGrok 4Grok 4.7
LMArena Text14111399
LMArena Creative Writing13971391
LMArena Multi-Turn14161393
Short-Story Creative Writing76.9%—
EQ-Bench Creative Writing—2007
WildBench79.7%—

Frequently asked questions

Is Grok 4 better than Grok 4.7?

Grok 4.7 is the stronger model overall, scoring 53.1 to 48.1 on the Noometry Index.

Is Grok 4 or Grok 4.7 better for coding?

Grok 4.7 scores higher on coding benchmarks: 58.0 versus 50.3 in the Noometry coding category.

How many benchmarks do Grok 4 and Grok 4.7 share?

19 benchmarks have published results for both models. Grok 4 has 48 scored results on Noometry and Grok 4.7 has 39.

Related comparisons

Go deeper