Noometry

Model comparison

Claude Sonnet 4 vs Grok 4.20 (Non-Reasoning)

Grok 4.20 (Non-Reasoning) is the stronger model overall, scoring 48.6 to 40.8 on the Noometry Index.

Last verified . 30 shared benchmarks.

Claude Sonnet 4 Anthropic

40.8

Rank #145 Confirmed

Grok 4.20 (Non-Reasoning) xAI

48.6

Rank #54 Confirmed

Summary

  • They share 30 benchmarks with published results for both. Claude Sonnet 4 scores higher in 2 categories and Grok 4.20 (Non-Reasoning) in 8 categories; 10 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Grok 4.20 (Non-Reasoning) leads 52.3 to 22.9.
  • The biggest single-benchmark swing is ARC-AGI-2: 5.9% for Claude Sonnet 4 and 65.1% for Grok 4.20 (Non-Reasoning).
  • Grok 4.20 (Non-Reasoning) is cheaper at $1.25 / $2.50 per million input/output tokens, against $3 / $15 for Claude Sonnet 4.
  • Grok 4.20 (Non-Reasoning) accepts more context: 1M tokens versus 200K.

Side by side

Claude Sonnet 4Grok 4.20 (Non-Reasoning)
ProviderAnthropicxAI
Noometry Index40.848.6
Released2025-05-222026-02-17
WeightsProprietaryProprietary
Context window200K1M
Max output64K30K
Input $ / M tokens$3$1.25
Output $ / M tokens$15$2.50
Results tracked5846

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

Category by category

Coding Claude Sonnet 4 leads

Claude Sonnet 4: 43.5 (#88), Grok 4.20 (Non-Reasoning): 42.1 (#112)

BenchmarkClaude Sonnet 4Grok 4.20 (Non-Reasoning)
WeirdML46.1%52.3%
LMArena Coding14141459
ALE-Bench655.351,150
SWE-bench Verified (bash only)64.9%—
Aider Polyglot61.3%—
LMArena WebDev—1375
SciCode40%—
GSO4.9%—

Agentic & Tool Use Claude Sonnet 4 leads

Claude Sonnet 4: 38.5 (#31), Grok 4.20 (Non-Reasoning): 34.4 (#46)

BenchmarkClaude Sonnet 4Grok 4.20 (Non-Reasoning)
Terminal-Bench—57.3%
TheAgentCompany33.1%—
τ²-bench Banking—18%
Cybench35%—
DeepResearch Bench46.6%—
OSWorld43.9%—
LMArena Search—1189
METR Time Horizons62%—
Vending-Bench 2—4,663

Reasoning Grok 4.20 (Non-Reasoning) leads

Claude Sonnet 4: 22.9 (#187), Grok 4.20 (Non-Reasoning): 52.3 (#32)

BenchmarkClaude Sonnet 4Grok 4.20 (Non-Reasoning)
ARC-AGI-25.9%65.1%
Kagi LLM Benchmark73%75%
ARC-AGI-140%89.5%
LMArena Hard Prompts13721451
DTBench77.1%90.1%
LMCA29%38.7%
Epoch Capabilities Index141.69151.98
ForecastBench60.261.4
SimpleBench45.5%—
NYT Connections (extended)—85.4%
CritPt0.3%—
Chess Puzzles—24%
EnigmaEval3.1%—
Thematic Generalization—63.8%

Math Grok 4.20 (Non-Reasoning) leads

Claude Sonnet 4: 43.3 (#80), Grok 4.20 (Non-Reasoning): 48.2 (#65)

BenchmarkClaude Sonnet 4Grok 4.20 (Non-Reasoning)
OTIS Mock AIME 2024-202571.1%92.2%
LMArena Math13751455
FrontierMath (Tiers 1-3)—44.9%
FrontierMath Tier 4—17.1%
ProofBench—14%
Omni-MATH60.2%—
MATH Level 584.4%—
FrontierMath (Feb 2025 set)4.1%—
FrontierMath Tier 4 (v1)0%—

Knowledge Grok 4.20 (Non-Reasoning) leads

Claude Sonnet 4: 41.8 (#108), Grok 4.20 (Non-Reasoning): 52.8 (#60)

BenchmarkClaude Sonnet 4Grok 4.20 (Non-Reasoning)
GPQA Diamond79.2%89.3%
LMArena Expert13721439
Humanity's Last Exam7.8%—
SimpleQA Verified—30.2%
MMLU-Pro84.3%—
Confabulations13.2%—
Vectara Hallucination Rate10.3%—
GPQA (HELM)70.6%—

Multimodal Grok 4.20 (Non-Reasoning) leads

Claude Sonnet 4: 26.2 (#121), Grok 4.20 (Non-Reasoning): 33.3 (#98)

BenchmarkClaude Sonnet 4Grok 4.20 (Non-Reasoning)
LMArena Vision11911263
GeoBench37%—
VPCT34%—
Blueprint-Bench 2—0%
LMArena Document—1416
MindCube44.8%—

Multilingual Grok 4.20 (Non-Reasoning) leads

Claude Sonnet 4: 46.7 (#156), Grok 4.20 (Non-Reasoning): 54.5 (#40)

BenchmarkClaude Sonnet 4Grok 4.20 (Non-Reasoning)
LMArena Non-English13331441
LMArena Chinese13501481
LMArena French13631476
LMArena German13311465
LMArena Japanese13021449
LMArena Korean12911417
LMArena Russian13551458
LMArena Spanish13571443

Instruction Following Grok 4.20 (Non-Reasoning) leads

Claude Sonnet 4: 71.7 (#145), Grok 4.20 (Non-Reasoning): 74.8 (#83)

BenchmarkClaude Sonnet 4Grok 4.20 (Non-Reasoning)
LMArena Instruction Following13761420
IFEval84%—

Long Context Grok 4.20 (Non-Reasoning) leads

Claude Sonnet 4: 33.7 (#259), Grok 4.20 (Non-Reasoning): 45.5 (#34)

BenchmarkClaude Sonnet 4Grok 4.20 (Non-Reasoning)
LMArena Longer Query13981437
Fiction.LiveBench46.9%—
CL-bench—22.2%
CL-bench Life—11.9%

Writing & Preference Grok 4.20 (Non-Reasoning) leads

Claude Sonnet 4: 57.1 (#132), Grok 4.20 (Non-Reasoning): 65.7 (#44)

BenchmarkClaude Sonnet 4Grok 4.20 (Non-Reasoning)
LMArena Text13511451
LMArena Creative Writing13451438
EQ-Bench Creative Writing14831574
LMArena Multi-Turn13761456
Short-Story Creative Writing81.4%—
WildBench83.8%—

Frequently asked questions

Is Claude Sonnet 4 better than Grok 4.20 (Non-Reasoning)?

Grok 4.20 (Non-Reasoning) is the stronger model overall, scoring 48.6 to 40.8 on the Noometry Index.

Which is cheaper, Claude Sonnet 4 or Grok 4.20 (Non-Reasoning)?

Grok 4.20 (Non-Reasoning) is cheaper. It lists at $1.25 per million input tokens and $2.50 per million output tokens; Claude Sonnet 4 lists at $3 and $15.

Is Claude Sonnet 4 or Grok 4.20 (Non-Reasoning) better for coding?

Claude Sonnet 4 scores higher on coding benchmarks: 43.5 versus 42.1 in the Noometry coding category.

Which has the bigger context window?

Grok 4.20 (Non-Reasoning) does, with 1M tokens against 200K.

How many benchmarks do Claude Sonnet 4 and Grok 4.20 (Non-Reasoning) share?

30 benchmarks have published results for both models. Claude Sonnet 4 has 58 scored results on Noometry and Grok 4.20 (Non-Reasoning) has 46.

Related comparisons

Go deeper