Noometry

Model comparison

Grok-2 (Dec 2024) vs Grok 4.7

Grok 4.7 is the stronger model overall, scoring 53.1 to 33.7 on the Noometry Index.

Last verified . 18 shared benchmarks.

Grok-2 (Dec 2024) xAI

33.7

Rank #239 Confirmed

Grok 4.7 xAI

53.1

Rank #37 Confirmed

Summary

  • They share 18 benchmarks with published results for both. Grok-2 (Dec 2024) scores higher in 0 categories and Grok 4.7 in 8 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in math, where Grok 4.7 leads 57.8 to 20.8.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 11.5% for Grok-2 (Dec 2024) and 98.1% for Grok 4.7.

Side by side

Grok-2 (Dec 2024)Grok 4.7
ProviderxAIxAI
Noometry Index33.753.1
Released2024-08-132026-09-21
WeightsProprietaryProprietary
Context window—500K
Max output—500K
Input $ / M tokens—$2
Output $ / M tokens—$6
Results tracked3439

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

Category by category

Coding Grok 4.7 leads

Grok-2 (Dec 2024): 33.3 (#258), Grok 4.7: 58.0 (#18)

BenchmarkGrok-2 (Dec 2024)Grok 4.7
LMArena Coding12871427
FrontierCode—47.6%
CursorBench—46.3%
LMArena WebDev—1639
FrontierSWE—29.5%
SciCode—57.8%
WeirdML22.2%—
LiveBench Coding46.4%—

Agentic & Tool Use Not comparable

Grok-2 (Dec 2024): —, Grok 4.7: 36.7 (#37)

BenchmarkGrok-2 (Dec 2024)Grok 4.7
APEX-Agents—54.6%
GDP.pdf—22.8%
Vending-Bench 2—10,537

Reasoning Grok 4.7 leads

Grok-2 (Dec 2024): 16.9 (#299), Grok 4.7: 49.1 (#40)

BenchmarkGrok-2 (Dec 2024)Grok 4.7
LMArena Hard Prompts12721413
DTBench65.2%96%
Epoch Capabilities Index130.48153.53
SimpleBench22.7%—
NYT Connections (extended)—76.8%
CritPt—18%
Chess Puzzles—38%
LiveBench Reasoning54.8%—
Mystery Game Puzzles—29%
LiveBench Data Analysis54.5%—
LMCA—49.4%
LiveBench54.3%—

Math Grok 4.7 leads

Grok-2 (Dec 2024): 20.8 (#284), Grok 4.7: 57.8 (#39)

BenchmarkGrok-2 (Dec 2024)Grok 4.7
OTIS Mock AIME 2024-202511.5%98.1%
LMArena Math12831407
FrontierMath (Tiers 1-3)—53%
FrontierMath Tier 4—17.1%
ProofBench—34%
LiveBench Math54.9%—
MATH Level 563.5%—
FrontierMath (Feb 2025 set)0.7%—

Knowledge Grok 4.7 leads

Grok-2 (Dec 2024): 29.8 (#233), Grok 4.7: 62.8 (#22)

BenchmarkGrok-2 (Dec 2024)Grok 4.7
GPQA Diamond53.8%92.7%
LMArena Expert12541422
SimpleQA Verified—56%
Confabulations20.1%—

Multimodal Not comparable

Grok-2 (Dec 2024): —, Grok 4.7: 35.5 (#87)

BenchmarkGrok-2 (Dec 2024)Grok 4.7
LMArena Vision—1228
Blueprint-Bench 2—32.5%
Furniture Assembly—20.8%

Multilingual Grok 4.7 leads

Grok-2 (Dec 2024): 43.1 (#188), Grok 4.7: 50.8 (#116)

BenchmarkGrok-2 (Dec 2024)Grok 4.7
LMArena Non-English12821389
LMArena Chinese12891455
LMArena French13181455
LMArena Russian12861397
LMArena Spanish12811400
LMArena German1287—
LMArena Japanese1244—
LMArena Korean1237—

Instruction Following Grok 4.7 leads

Grok-2 (Dec 2024): 66.9 (#202), Grok 4.7: 74.1 (#105)

BenchmarkGrok-2 (Dec 2024)Grok 4.7
LMArena Instruction Following12701404
LiveBench Instruction Following69.6%—

Long Context Grok 4.7 leads

Grok-2 (Dec 2024): 38.8 (#190), Grok 4.7: 43.1 (#104)

BenchmarkGrok-2 (Dec 2024)Grok 4.7
LMArena Longer Query12761413

Writing & Preference Grok 4.7 leads

Grok-2 (Dec 2024): 48.6 (#198), Grok 4.7: 70.0 (#24)

BenchmarkGrok-2 (Dec 2024)Grok 4.7
LMArena Text13051399
LMArena Creative Writing12841391
LMArena Multi-Turn12901393
Short-Story Creative Writing63.6%—
EQ-Bench Creative Writing—2007
LiveBench Language45.6%—

Frequently asked questions

Is Grok-2 (Dec 2024) better than Grok 4.7?

Grok 4.7 is the stronger model overall, scoring 53.1 to 33.7 on the Noometry Index.

Is Grok-2 (Dec 2024) or Grok 4.7 better for coding?

Grok 4.7 scores higher on coding benchmarks: 58.0 versus 33.3 in the Noometry coding category.

How many benchmarks do Grok-2 (Dec 2024) and Grok 4.7 share?

18 benchmarks have published results for both models. Grok-2 (Dec 2024) has 34 scored results on Noometry and Grok 4.7 has 39.

Related comparisons

Go deeper