Noometry

Model comparison

Claude Sonnet 4.6 vs Grok 4.20 (Non-Reasoning)

Claude Sonnet 4.6 is the stronger model overall, scoring 50.3 to 48.6 on the Noometry Index. Grok 4.20 (Non-Reasoning) costs 3.8× less per token, which makes it the better buy when Claude Sonnet 4.6's lead doesn't matter for your workload.

Last verified . 40 shared benchmarks.

Claude Sonnet 4.6 Anthropic

50.3

Rank #50 Confirmed

Grok 4.20 (Non-Reasoning) xAI

48.6

Rank #54 Confirmed

Summary

  • They share 40 benchmarks with published results for both. Claude Sonnet 4.6 scores higher in 6 categories and Grok 4.20 (Non-Reasoning) in 4 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Grok 4.20 (Non-Reasoning) leads 52.3 to 46.1.
  • The biggest single-benchmark swing is ProofBench: 45% for Claude Sonnet 4.6 and 14% 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 4.6.

Side by side

Claude Sonnet 4.6Grok 4.20 (Non-Reasoning)
ProviderAnthropicxAI
Noometry Index50.348.6
Released2026-02-172026-02-17
WeightsProprietaryProprietary
Context window1M1M
Max output128K30K
Input $ / M tokens$3$1.25
Output $ / M tokens$15$2.50
Results tracked5746

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

Category by category

Coding Claude Sonnet 4.6 leads

Claude Sonnet 4.6: 46.3 (#67), Grok 4.20 (Non-Reasoning): 42.1 (#112)

BenchmarkClaude Sonnet 4.6Grok 4.20 (Non-Reasoning)
LMArena WebDev15221375
WeirdML66.1%52.3%
LMArena Coding15041459
ALE-Bench1,3271,150
SWE-bench Verified75.2%—
DeepSWE29.9%—
FrontierCode24.3%—
SciCode46.8%—

Agentic & Tool Use Claude Sonnet 4.6 leads

Claude Sonnet 4.6: 39.1 (#28), Grok 4.20 (Non-Reasoning): 34.4 (#46)

BenchmarkClaude Sonnet 4.6Grok 4.20 (Non-Reasoning)
Terminal-Bench53.4%57.3%
LMArena Search12211189
Vending-Bench 27,2044,663
APEX-Agents43%—
OSWorld 2.09.3%—
τ²-bench Banking—18%
DeepResearch Bench54.9%—
OSWorld72.1%—
ExploitBench23.6%—
GBAEval48.8%—
GDP.pdf18%—

Reasoning Grok 4.20 (Non-Reasoning) leads

Claude Sonnet 4.6: 46.1 (#45), Grok 4.20 (Non-Reasoning): 52.3 (#32)

BenchmarkClaude Sonnet 4.6Grok 4.20 (Non-Reasoning)
ARC-AGI-260.4%65.1%
NYT Connections (extended)80.9%85.4%
ARC-AGI-186.5%89.5%
Chess Puzzles13%24%
Thematic Generalization76.3%63.8%
LMArena Hard Prompts14841451
DTBench89.9%90.1%
LMCA46.5%38.7%
Epoch Capabilities Index152.24151.98
ForecastBench6261.4
Kagi LLM Benchmark—75%
CritPt3.1%—
Mystery Game Puzzles16%—

Math Claude Sonnet 4.6 leads

Claude Sonnet 4.6: 52.9 (#49), Grok 4.20 (Non-Reasoning): 48.2 (#65)

BenchmarkClaude Sonnet 4.6Grok 4.20 (Non-Reasoning)
OTIS Mock AIME 2024-202585.8%92.2%
ProofBench45%14%
LMArena Math14621455
FrontierMath (Tiers 1-3)—44.9%
FrontierMath Tier 4—17.1%
FrontierMath (Feb 2025 set)32.4%—
FrontierMath Tier 4 (v1)8.3%—

Knowledge Grok 4.20 (Non-Reasoning) leads

Claude Sonnet 4.6: 51.7 (#65), Grok 4.20 (Non-Reasoning): 52.8 (#60)

BenchmarkClaude Sonnet 4.6Grok 4.20 (Non-Reasoning)
GPQA Diamond87.4%89.3%
SimpleQA Verified35.5%30.2%
LMArena Expert15001439
Vectara Hallucination Rate10.6%—

Multimodal Claude Sonnet 4.6 leads

Claude Sonnet 4.6: 38.0 (#68), Grok 4.20 (Non-Reasoning): 33.3 (#98)

BenchmarkClaude Sonnet 4.6Grok 4.20 (Non-Reasoning)
LMArena Vision12831263
Blueprint-Bench 26.7%0%
LMArena Document14821416

Multilingual Too close to call

Claude Sonnet 4.6: 54.4 (#41), Grok 4.20 (Non-Reasoning): 54.5 (#40)

BenchmarkClaude Sonnet 4.6Grok 4.20 (Non-Reasoning)
LMArena Non-English14401441
LMArena Chinese14911481
LMArena French14651476
LMArena German14281465
LMArena Japanese14201449
LMArena Korean14111417
LMArena Russian14401458
LMArena Spanish14641443

Instruction Following Claude Sonnet 4.6 leads

Claude Sonnet 4.6: 77.4 (#25), Grok 4.20 (Non-Reasoning): 74.8 (#83)

BenchmarkClaude Sonnet 4.6Grok 4.20 (Non-Reasoning)
LMArena Instruction Following14751420

Long Context Too close to call

Claude Sonnet 4.6: 45.3 (#44), Grok 4.20 (Non-Reasoning): 45.5 (#34)

BenchmarkClaude Sonnet 4.6Grok 4.20 (Non-Reasoning)
LMArena Longer Query14791437
CL-bench—22.2%
CL-bench Life—11.9%

Writing & Preference Claude Sonnet 4.6 leads

Claude Sonnet 4.6: 70.2 (#22), Grok 4.20 (Non-Reasoning): 65.7 (#44)

BenchmarkClaude Sonnet 4.6Grok 4.20 (Non-Reasoning)
LMArena Text14581451
LMArena Creative Writing14351438
EQ-Bench Creative Writing18101574
LMArena Multi-Turn14641456
EQ-Bench 41207—

Frequently asked questions

Is Claude Sonnet 4.6 better than Grok 4.20 (Non-Reasoning)?

Claude Sonnet 4.6 is the stronger model overall, scoring 50.3 to 48.6 on the Noometry Index. Grok 4.20 (Non-Reasoning) costs 3.8× less per token, which makes it the better buy when Claude Sonnet 4.6's lead doesn't matter for your workload.

Which is cheaper, Claude Sonnet 4.6 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 4.6 lists at $3 and $15.

Is Claude Sonnet 4.6 or Grok 4.20 (Non-Reasoning) better for coding?

Claude Sonnet 4.6 scores higher on coding benchmarks: 46.3 versus 42.1 in the Noometry coding category.

Which has the bigger context window?

Both accept 1M tokens.

How many benchmarks do Claude Sonnet 4.6 and Grok 4.20 (Non-Reasoning) share?

40 benchmarks have published results for both models. Claude Sonnet 4.6 has 57 scored results on Noometry and Grok 4.20 (Non-Reasoning) has 46.

Related comparisons

Go deeper