Noometry

Model comparison

Claude Sonnet 4.6 vs Grok 4

Claude Sonnet 4.6 is the stronger model overall, scoring 50.1 to 47.8 on the Noometry Index.

Last verified . 31 shared benchmarks.

Claude Sonnet 4.6 Anthropic

50.1

Rank #42 Confirmed

Grok 4 xAI

47.8

Rank #49 Confirmed

Summary

  • They share 31 benchmarks with published results for both. Claude Sonnet 4.6 scores higher in 6 categories and Grok 4 in 4 categories; 10 gaps are clear of the uncertainty.
  • The widest gap is in long context, where Grok 4 leads 63.1 to 45.3.
  • The biggest single-benchmark swing is ARC-AGI-2: 60.4% for Claude Sonnet 4.6 and 16% for Grok 4.

Side by side

Claude Sonnet 4.6Grok 4
ProviderAnthropicxAI
Noometry Index50.147.8
Released2026-02-172025-07-09
WeightsProprietaryProprietary
Context window1M—
Max output128K—
Input $ / M tokens$3—
Output $ / M tokens$15—
Results tracked5748

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

Category by category

Coding Grok 4 leads

Claude Sonnet 4.6: 46.0 (#62), Grok 4: 49.9 (#44)

BenchmarkClaude Sonnet 4.6Grok 4
WeirdML66.1%45.7%
LMArena Coding15041408
SWE-bench Verified75.2%—
DeepSWE29.9%—
FrontierCode24.3%—
Aider Polyglot—79.6%
LMArena WebDev1521—
SciCode46.8%—
ALE-Bench1,327—

Agentic & Tool Use Claude Sonnet 4.6 leads

Claude Sonnet 4.6: 39.1 (#26), Grok 4: 32.1 (#62)

BenchmarkClaude Sonnet 4.6Grok 4
Terminal-Bench53.4%27.2%
DeepResearch Bench54.9%47.3%
LMArena Search12211142
APEX-Agents43%—
Berkeley Function Calling Leaderboard—63%
OSWorld 2.09.3%—
GDPval—21.1%
Cybench—43%
OSWorld72.1%—
BALROG—43.6%
ExploitBench23.6%—
GBAEval48.8%—
GDP.pdf18%—
METR Time Horizons—66.6%
Vending-Bench 27,204—

Reasoning Claude Sonnet 4.6 leads

Claude Sonnet 4.6: 46.1 (#40), Grok 4: 36.9 (#59)

BenchmarkClaude Sonnet 4.6Grok 4
ARC-AGI-260.4%16%
ARC-AGI-186.5%66.7%
Chess Puzzles13%28%
LMArena Hard Prompts14851409
Epoch Capabilities Index152.25146.46
ForecastBench6260.9
SimpleBench—60.5%
Kagi LLM Benchmark—73.6%
NYT Connections (extended)80.9%—
CritPt3.1%—
Thematic Generalization76.3%—
Mystery Game Puzzles16%—
DTBench89.9%—
LMCA46.5%—

Math Claude Sonnet 4.6 leads

Claude Sonnet 4.6: 51.9 (#41), Grok 4: 46.5 (#58)

BenchmarkClaude Sonnet 4.6Grok 4
OTIS Mock AIME 2024-202585.8%84%
LMArena Math14631422
FrontierMath (Feb 2025 set)32.4%19.7%
FrontierMath Tier 4 (v1)8.3%2.1%
ProofBench45%—
Omni-MATH—60.3%

Knowledge Grok 4 leads

Claude Sonnet 4.6: 51.6 (#60), Grok 4: 53.7 (#50)

BenchmarkClaude Sonnet 4.6Grok 4
GPQA Diamond87.4%87%
LMArena Expert15001417
SimpleQA Verified35.5%—
MMLU-Pro—85.1%
Confabulations—12.4%
Vectara Hallucination Rate10.6%—
GPQA (HELM)—72.7%

Multimodal Claude Sonnet 4.6 leads

Claude Sonnet 4.6: 38.0 (#61), Grok 4: 33.1 (#89)

BenchmarkClaude Sonnet 4.6Grok 4
LMArena Vision12831211
GeoBench—45%
Blueprint-Bench 26.7%—
LMArena Document1482—

Multilingual Claude Sonnet 4.6 leads

Claude Sonnet 4.6: 54.6 (#39), Grok 4: 52.0 (#98)

BenchmarkClaude Sonnet 4.6Grok 4
LMArena Non-English14401403
LMArena Chinese14911428
LMArena French14651418
LMArena German14281429
LMArena Japanese14191396
LMArena Korean14111376
LMArena Russian14401409
LMArena Spanish14651419

Instruction Following Grok 4 leads

Claude Sonnet 4.6: 77.6 (#23), Grok 4: 79.4 (#4)

BenchmarkClaude Sonnet 4.6Grok 4
LMArena Instruction Following14761387
IFEval—94.9%

Long Context Grok 4 leads

Claude Sonnet 4.6: 45.3 (#40), Grok 4: 63.1 (#4)

BenchmarkClaude Sonnet 4.6Grok 4
LMArena Longer Query14791409
Fiction.LiveBench—94.4%

Writing & Preference Claude Sonnet 4.6 leads

Claude Sonnet 4.6: 70.4 (#22), Grok 4: 58.7 (#111)

BenchmarkClaude Sonnet 4.6Grok 4
LMArena Text14581412
LMArena Creative Writing14351397
LMArena Multi-Turn14641416
Short-Story Creative Writing—76.9%
EQ-Bench Creative Writing1810—
WildBench—79.7%
EQ-Bench 41207—

Frequently asked questions

Is Claude Sonnet 4.6 better than Grok 4?

Claude Sonnet 4.6 is the stronger model overall, scoring 50.1 to 47.8 on the Noometry Index.

Is Claude Sonnet 4.6 or Grok 4 better for coding?

Grok 4 scores higher on coding benchmarks: 49.9 versus 46.0 in the Noometry coding category.

How many benchmarks do Claude Sonnet 4.6 and Grok 4 share?

31 benchmarks have published results for both models. Claude Sonnet 4.6 has 57 scored results on Noometry and Grok 4 has 48.

Related comparisons

Go deeper