Noometry

Model comparison

Grok 3 vs Grok 4.7

Grok 4.7 is the stronger model overall, scoring 53.1 to 39.9 on the Noometry Index.

Last verified . 18 shared benchmarks.

Grok 3 xAI

39.9

Rank #157 Confirmed

Grok 4.7 xAI

53.1

Rank #37 Confirmed

Summary

  • They share 18 benchmarks with published results for both. Grok 3 scores higher in 2 categories and Grok 4.7 in 7 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Grok 4.7 leads 49.1 to 13.7.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 55.6% for Grok 3 and 98.1% for Grok 4.7.

Side by side

Grok 3Grok 4.7
ProviderxAIxAI
Noometry Index39.953.1
Released2025-04-092026-09-21
WeightsProprietaryProprietary
Context window—500K
Max output—500K
Input $ / M tokens—$2
Output $ / M tokens—$6
Results tracked4039

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

Category by category

Coding Grok 4.7 leads

Grok 3: 41.9 (#115), Grok 4.7: 58.0 (#18)

BenchmarkGrok 3Grok 4.7
LMArena Coding14321427
FrontierCode—47.6%
Aider Polyglot53.3%—
CursorBench—46.3%
LMArena WebDev—1639
FrontierSWE—29.5%
SciCode—57.8%
WeirdML37.2%—

Agentic & Tool Use Grok 4.7 leads

Grok 3: 30.5 (#76), Grok 4.7: 36.7 (#37)

BenchmarkGrok 3Grok 4.7
APEX-Agents—54.6%
BALROG29.5%—
GDP.pdf—22.8%
Vending-Bench 2—10,537

Reasoning Grok 4.7 leads

Grok 3: 13.7 (#333), Grok 4.7: 49.1 (#40)

BenchmarkGrok 3Grok 4.7
LMArena Hard Prompts14341413
Epoch Capabilities Index138.33153.53
ARC-AGI-20%—
SimpleBench36.1%—
Kagi LLM Benchmark61.3%—
NYT Connections (extended)—76.8%
ARC-AGI-15.5%—
CritPt—18%
Chess Puzzles—38%
Mystery Game Puzzles—29%
DTBench—96%
LMCA—49.4%

Math Grok 4.7 leads

Grok 3: 38.0 (#145), Grok 4.7: 57.8 (#39)

BenchmarkGrok 3Grok 4.7
OTIS Mock AIME 2024-202555.6%98.1%
LMArena Math13911407
FrontierMath (Tiers 1-3)—53%
FrontierMath Tier 4—17.1%
ProofBench—34%
Omni-MATH46.4%—
MATH Level 588.7%—
FrontierMath (Feb 2025 set)3.8%—
FrontierMath Tier 4 (v1)0%—

Knowledge Grok 4.7 leads

Grok 3: 46.2 (#82), Grok 4.7: 62.8 (#22)

BenchmarkGrok 3Grok 4.7
GPQA Diamond75.8%92.7%
LMArena Expert14211422
SimpleQA Verified—56%
MMLU-Pro78.8%—
Confabulations14.2%—
Vectara Hallucination Rate5.8%—
GPQA (HELM)65%—

Multimodal Not comparable

Grok 3: —, Grok 4.7: 35.5 (#87)

BenchmarkGrok 3Grok 4.7
LMArena Vision—1228
Blueprint-Bench 2—32.5%
Furniture Assembly—20.8%

Multilingual Grok 3 leads

Grok 3: 52.3 (#87), Grok 4.7: 50.8 (#116)

BenchmarkGrok 3Grok 4.7
LMArena Non-English14101389
LMArena Chinese14481455
LMArena French14601455
LMArena Russian14161397
LMArena Spanish14171400
LMArena German1431—
LMArena Japanese1387—
LMArena Korean1373—

Instruction Following Too close to call

Grok 3: 75.0 (#73), Grok 4.7: 74.1 (#105)

BenchmarkGrok 3Grok 4.7
LMArena Instruction Following14091404
IFEval88.4%—

Long Context Grok 4.7 leads

Grok 3: 38.7 (#192), Grok 4.7: 43.1 (#104)

BenchmarkGrok 3Grok 4.7
LMArena Longer Query14391413
Fiction.LiveBench58.3%—

Writing & Preference Grok 4.7 leads

Grok 3: 55.8 (#141), Grok 4.7: 70.0 (#24)

BenchmarkGrok 3Grok 4.7
LMArena Text14261399
LMArena Creative Writing14141391
EQ-Bench Creative Writing11862007
LMArena Multi-Turn14251393
Short-Story Creative Writing76.4%—
WildBench84.9%—

Frequently asked questions

Is Grok 3 better than Grok 4.7?

Grok 4.7 is the stronger model overall, scoring 53.1 to 39.9 on the Noometry Index.

Is Grok 3 or Grok 4.7 better for coding?

Grok 4.7 scores higher on coding benchmarks: 58.0 versus 41.9 in the Noometry coding category.

How many benchmarks do Grok 3 and Grok 4.7 share?

18 benchmarks have published results for both models. Grok 3 has 40 scored results on Noometry and Grok 4.7 has 39.

Related comparisons

Go deeper