Noometry

Model comparison

Claude 3 Sonnet vs Grok 4.6

Grok 4.6 is the stronger model overall, scoring 56.9 to 29.0 on the Noometry Index.

Last verified . 23 shared benchmarks.

Claude 3 Sonnet Anthropic

29.0

Rank #319 Confirmed

Grok 4.6 xAI

56.9

Rank #21 Confirmed

Summary

  • They share 23 benchmarks with published results for both. Claude 3 Sonnet scores higher in 0 categories and Grok 4.6 in 9 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in math, where Grok 4.6 leads 67.0 to 10.7.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 2.5% for Claude 3 Sonnet and 99.2% for Grok 4.6.

Side by side

Claude 3 SonnetGrok 4.6
ProviderAnthropicxAI
Noometry Index29.056.9
Released2024-02-292026-08-12
WeightsProprietaryProprietary
Context window—500K
Max output—500K
Input $ / M tokens—$2
Output $ / M tokens—$6
Results tracked3049

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

Category by category

Coding Grok 4.6 leads

Claude 3 Sonnet: 29.6 (#302), Grok 4.6: 58.5 (#16)

BenchmarkClaude 3 SonnetGrok 4.6
WeirdML10.2%67.3%
LMArena Coding12231465
DeepSWE—67.5%
FrontierCode—48%
CursorBench—41.4%
LMArena WebDev—1617
FrontierSWE—25.3%
SciCode—56.5%
BigCodeBench Instruct42.7%—
BigCodeBench Complete53.8%—
ALE-Bench—1,508
HumanEval+64%—
MBPP+69.3%—

Agentic & Tool Use Not comparable

Claude 3 Sonnet: —, Grok 4.6: 39.4 (#27)

BenchmarkClaude 3 SonnetGrok 4.6
APEX-Agents—65.3%
GDP.pdf—17.2%
Vending-Bench 2—9,047

Reasoning Grok 4.6 leads

Claude 3 Sonnet: 20.5 (#237), Grok 4.6: 61.4 (#20)

BenchmarkClaude 3 SonnetGrok 4.6
LMArena Hard Prompts11971447
DTBench53.6%97.3%
Epoch Capabilities Index120.7156.44
ARC-AGI-2—67.1%
SimpleBench—75.9%
NYT Connections (extended)—80%
ARC-AGI-1—87.5%
CritPt—19.7%
Chess Puzzles—40%
EBR-Bench—30.5%
Mystery Game Puzzles—34%
LMCA—48.5%
WinoGrande75.1%—

Math Grok 4.6 leads

Claude 3 Sonnet: 10.7 (#310), Grok 4.6: 67.0 (#24)

BenchmarkClaude 3 SonnetGrok 4.6
OTIS Mock AIME 2024-20252.5%99.2%
LMArena Math12131423
FrontierMath (Tiers 1-3)—66%
FrontierMath Tier 4—31.7%
ProofBench—51%
MATH Level 518.2%—

Knowledge Grok 4.6 leads

Claude 3 Sonnet: 21.1 (#276), Grok 4.6: 63.3 (#20)

BenchmarkClaude 3 SonnetGrok 4.6
GPQA Diamond40.6%94%
LMArena Expert11731467
SimpleQA Verified—49.3%
MMLU75.9%—

Multimodal Grok 4.6 leads

Claude 3 Sonnet: 25.2 (#125), Grok 4.6: 43.6 (#23)

BenchmarkClaude 3 SonnetGrok 4.6
LMArena Vision9841263
Blueprint-Bench 2—33.2%
Furniture Assembly—40%
LMArena Document—1452

Multilingual Grok 4.6 leads

Claude 3 Sonnet: 37.8 (#234), Grok 4.6: 53.0 (#74)

BenchmarkClaude 3 SonnetGrok 4.6
LMArena Non-English12051420
LMArena Chinese11891480
LMArena French12291461
LMArena German12041431
LMArena Japanese11311376
LMArena Korean11281397
LMArena Russian12271422
LMArena Spanish12041404

Instruction Following Grok 4.6 leads

Claude 3 Sonnet: 62.8 (#235), Grok 4.6: 75.4 (#63)

BenchmarkClaude 3 SonnetGrok 4.6
LMArena Instruction Following11991431

Long Context Grok 4.6 leads

Claude 3 Sonnet: 36.7 (#228), Grok 4.6: 44.5 (#66)

BenchmarkClaude 3 SonnetGrok 4.6
LMArena Longer Query12111454

Writing & Preference Grok 4.6 leads

Claude 3 Sonnet: 42.1 (#238), Grok 4.6: 62.3 (#80)

BenchmarkClaude 3 SonnetGrok 4.6
LMArena Text12181428
LMArena Creative Writing11861428
LMArena Multi-Turn12271425

Frequently asked questions

Is Claude 3 Sonnet better than Grok 4.6?

Grok 4.6 is the stronger model overall, scoring 56.9 to 29.0 on the Noometry Index.

Is Claude 3 Sonnet or Grok 4.6 better for coding?

Grok 4.6 scores higher on coding benchmarks: 58.5 versus 29.6 in the Noometry coding category.

How many benchmarks do Claude 3 Sonnet and Grok 4.6 share?

23 benchmarks have published results for both models. Claude 3 Sonnet has 30 scored results on Noometry and Grok 4.6 has 49.

Related comparisons

Go deeper