Noometry

Model comparison

Grok-2 (Dec 2024) vs Grok 4.6

Grok 4.6 is the stronger model overall, scoring 56.9 to 33.7 on the Noometry Index.

Last verified . 23 shared benchmarks.

Grok-2 (Dec 2024) xAI

33.7

Rank #239 Confirmed

Grok 4.6 xAI

56.9

Rank #21 Confirmed

Summary

  • They share 23 benchmarks with published results for both. Grok-2 (Dec 2024) 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 20.8.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 11.5% for Grok-2 (Dec 2024) and 99.2% for Grok 4.6.

Side by side

Grok-2 (Dec 2024)Grok 4.6
ProviderxAIxAI
Noometry Index33.756.9
Released2024-08-132026-08-12
WeightsProprietaryProprietary
Context window—500K
Max output—500K
Input $ / M tokens—$2
Output $ / M tokens—$6
Results tracked3449

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

Category by category

Coding Grok 4.6 leads

Grok-2 (Dec 2024): 33.3 (#258), Grok 4.6: 58.5 (#16)

BenchmarkGrok-2 (Dec 2024)Grok 4.6
WeirdML22.2%67.3%
LMArena Coding12871465
DeepSWE—67.5%
FrontierCode—48%
CursorBench—41.4%
LMArena WebDev—1617
FrontierSWE—25.3%
SciCode—56.5%
LiveBench Coding46.4%—
ALE-Bench—1,508

Agentic & Tool Use Not comparable

Grok-2 (Dec 2024): —, Grok 4.6: 39.4 (#27)

BenchmarkGrok-2 (Dec 2024)Grok 4.6
APEX-Agents—65.3%
GDP.pdf—17.2%
Vending-Bench 2—9,047

Reasoning Grok 4.6 leads

Grok-2 (Dec 2024): 16.9 (#299), Grok 4.6: 61.4 (#20)

BenchmarkGrok-2 (Dec 2024)Grok 4.6
SimpleBench22.7%75.9%
LMArena Hard Prompts12721447
DTBench65.2%97.3%
Epoch Capabilities Index130.48156.44
ARC-AGI-2—67.1%
NYT Connections (extended)—80%
ARC-AGI-1—87.5%
CritPt—19.7%
Chess Puzzles—40%
EBR-Bench—30.5%
LiveBench Reasoning54.8%—
Mystery Game Puzzles—34%
LiveBench Data Analysis54.5%—
LMCA—48.5%
LiveBench54.3%—

Math Grok 4.6 leads

Grok-2 (Dec 2024): 20.8 (#284), Grok 4.6: 67.0 (#24)

BenchmarkGrok-2 (Dec 2024)Grok 4.6
OTIS Mock AIME 2024-202511.5%99.2%
LMArena Math12831423
FrontierMath (Tiers 1-3)—66%
FrontierMath Tier 4—31.7%
ProofBench—51%
LiveBench Math54.9%—
MATH Level 563.5%—
FrontierMath (Feb 2025 set)0.7%—

Knowledge Grok 4.6 leads

Grok-2 (Dec 2024): 29.8 (#233), Grok 4.6: 63.3 (#20)

BenchmarkGrok-2 (Dec 2024)Grok 4.6
GPQA Diamond53.8%94%
LMArena Expert12541467
SimpleQA Verified—49.3%
Confabulations20.1%—

Multimodal Not comparable

Grok-2 (Dec 2024): —, Grok 4.6: 43.6 (#23)

BenchmarkGrok-2 (Dec 2024)Grok 4.6
LMArena Vision—1263
Blueprint-Bench 2—33.2%
Furniture Assembly—40%
LMArena Document—1452

Multilingual Grok 4.6 leads

Grok-2 (Dec 2024): 43.1 (#188), Grok 4.6: 53.0 (#74)

BenchmarkGrok-2 (Dec 2024)Grok 4.6
LMArena Non-English12821420
LMArena Chinese12891480
LMArena French13181461
LMArena German12871431
LMArena Japanese12441376
LMArena Korean12371397
LMArena Russian12861422
LMArena Spanish12811404

Instruction Following Grok 4.6 leads

Grok-2 (Dec 2024): 66.9 (#202), Grok 4.6: 75.4 (#63)

BenchmarkGrok-2 (Dec 2024)Grok 4.6
LMArena Instruction Following12701431
LiveBench Instruction Following69.6%—

Long Context Grok 4.6 leads

Grok-2 (Dec 2024): 38.8 (#190), Grok 4.6: 44.5 (#66)

BenchmarkGrok-2 (Dec 2024)Grok 4.6
LMArena Longer Query12761454

Writing & Preference Grok 4.6 leads

Grok-2 (Dec 2024): 48.6 (#198), Grok 4.6: 62.3 (#80)

BenchmarkGrok-2 (Dec 2024)Grok 4.6
LMArena Text13051428
LMArena Creative Writing12841428
LMArena Multi-Turn12901425
Short-Story Creative Writing63.6%—
LiveBench Language45.6%—

Frequently asked questions

Is Grok-2 (Dec 2024) better than Grok 4.6?

Grok 4.6 is the stronger model overall, scoring 56.9 to 33.7 on the Noometry Index.

Is Grok-2 (Dec 2024) or Grok 4.6 better for coding?

Grok 4.6 scores higher on coding benchmarks: 58.5 versus 33.3 in the Noometry coding category.

How many benchmarks do Grok-2 (Dec 2024) and Grok 4.6 share?

23 benchmarks have published results for both models. Grok-2 (Dec 2024) has 34 scored results on Noometry and Grok 4.6 has 49.

Related comparisons

Go deeper