Noometry

Model comparison

Claude Sonnet 4.6 vs Llama 4 Maverick

Claude Sonnet 4.6 is the stronger model overall, scoring 50.1 to 30.6 on the Noometry Index. Llama 4 Maverick costs 20× less per token, which makes it the better buy when Claude Sonnet 4.6's lead doesn't matter for your workload.

Last verified . 34 shared benchmarks.

Claude Sonnet 4.6 Anthropic

50.1

Rank #42 Confirmed

Llama 4 Maverick Meta

30.6

Rank #276 Confirmed

Summary

  • They share 34 benchmarks with published results for both. Claude Sonnet 4.6 scores higher in 10 categories and Llama 4 Maverick in 0 categories; 10 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Claude Sonnet 4.6 leads 46.1 to 10.1.
  • The biggest single-benchmark swing is ARC-AGI-1: 86.5% for Claude Sonnet 4.6 and 4.4% for Llama 4 Maverick.
  • Llama 4 Maverick is cheaper at $0.19 / $0.65 per million input/output tokens, against $3 / $15 for Claude Sonnet 4.6.
  • Claude Sonnet 4.6 accepts more context: 1M tokens versus 128K.
  • Llama 4 Maverick has downloadable open weights; the other is API-only.

Side by side

Claude Sonnet 4.6Llama 4 Maverick
ProviderAnthropicMeta
Noometry Index50.130.6
Released2026-02-172025-04-05
WeightsProprietaryOpen
Context window1M128K
Max output128K4K
Input $ / M tokens$3$0.19
Output $ / M tokens$15$0.65
Results tracked5754

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: 46.0 (#62), Llama 4 Maverick: 26.3 (#318)

BenchmarkClaude Sonnet 4.6Llama 4 Maverick
SciCode46.8%33.1%
WeirdML66.1%24.5%
LMArena Coding15041302
ALE-Bench1,327172.97
SWE-bench Verified75.2%—
DeepSWE29.9%—
FrontierCode24.3%—
SWE-bench Verified (bash only)—21%
Aider Polyglot—15.6%
LMArena WebDev1521—
BigCodeBench Instruct—49.7%
BigCodeBench Complete—61.4%

Agentic & Tool Use Claude Sonnet 4.6 leads

Claude Sonnet 4.6: 39.1 (#26), Llama 4 Maverick: 27.9 (#86)

BenchmarkClaude Sonnet 4.6Llama 4 Maverick
Terminal-Bench53.4%—
APEX-Agents43%—
Berkeley Function Calling Leaderboard—37.3%
OSWorld 2.09.3%—
DeepResearch Bench54.9%—
OSWorld72.1%—
ExploitBench23.6%—
GBAEval48.8%—
GDP.pdf18%—
LMArena Search1221—
Vending-Bench 27,204—

Reasoning Claude Sonnet 4.6 leads

Claude Sonnet 4.6: 46.1 (#40), Llama 4 Maverick: 10.1 (#337)

BenchmarkClaude Sonnet 4.6Llama 4 Maverick
ARC-AGI-260.4%0%
NYT Connections (extended)80.9%8%
ARC-AGI-186.5%4.4%
CritPt3.1%0%
LMArena Hard Prompts14851281
DTBench89.9%61.9%
LMCA46.5%15.9%
Epoch Capabilities Index152.25132.2
ForecastBench6257.5
SimpleBench—27.7%
Kagi LLM Benchmark—55.9%
Chess Puzzles13%—
EnigmaEval—0.6%
Thematic Generalization76.3%—
Mystery Game Puzzles16%—

Math Claude Sonnet 4.6 leads

Claude Sonnet 4.6: 51.9 (#41), Llama 4 Maverick: 24.6 (#256)

BenchmarkClaude Sonnet 4.6Llama 4 Maverick
OTIS Mock AIME 2024-202585.8%20.6%
LMArena Math14631299
FrontierMath (Feb 2025 set)32.4%0.7%
ProofBench45%—
Omni-MATH—42.2%
MATH Level 5—73%
FrontierMath Tier 4 (v1)8.3%—

Knowledge Claude Sonnet 4.6 leads

Claude Sonnet 4.6: 51.6 (#60), Llama 4 Maverick: 33.3 (#196)

BenchmarkClaude Sonnet 4.6Llama 4 Maverick
GPQA Diamond87.4%67%
Vectara Hallucination Rate10.6%8.2%
LMArena Expert15001259
Humanity's Last Exam—5.7%
SimpleQA Verified35.5%—
MMLU-Pro—81%
Confabulations—22.6%
GPQA (HELM)—65%

Multimodal Claude Sonnet 4.6 leads

Claude Sonnet 4.6: 38.0 (#61), Llama 4 Maverick: 30.9 (#100)

BenchmarkClaude Sonnet 4.6Llama 4 Maverick
LMArena Vision12831141
GeoBench—52%
Blueprint-Bench 26.7%—
LMArena Document1482—
SpatialViz-Bench—31.8%

Multilingual Claude Sonnet 4.6 leads

Claude Sonnet 4.6: 54.6 (#39), Llama 4 Maverick: 42.4 (#190)

BenchmarkClaude Sonnet 4.6Llama 4 Maverick
LMArena Non-English14401269
LMArena Chinese14911277
LMArena French14651258
LMArena German14281291
LMArena Japanese14191207
LMArena Korean14111203
LMArena Russian14401286
LMArena Spanish14651293

Instruction Following Claude Sonnet 4.6 leads

Claude Sonnet 4.6: 77.6 (#23), Llama 4 Maverick: 71.9 (#140)

BenchmarkClaude Sonnet 4.6Llama 4 Maverick
LMArena Instruction Following14761267
IFEval—90.8%

Long Context Claude Sonnet 4.6 leads

Claude Sonnet 4.6: 45.3 (#40), Llama 4 Maverick: 31.4 (#274)

BenchmarkClaude Sonnet 4.6Llama 4 Maverick
LMArena Longer Query14791280
Fiction.LiveBench—46.2%

Writing & Preference Claude Sonnet 4.6 leads

Claude Sonnet 4.6: 70.4 (#22), Llama 4 Maverick: 39.0 (#247)

BenchmarkClaude Sonnet 4.6Llama 4 Maverick
LMArena Text14581287
LMArena Creative Writing14351266
EQ-Bench Creative Writing1810860
LMArena Multi-Turn14641289
Short-Story Creative Writing—62%
WildBench—80%
EQ-Bench 41207—

Frequently asked questions

Is Claude Sonnet 4.6 better than Llama 4 Maverick?

Claude Sonnet 4.6 is the stronger model overall, scoring 50.1 to 30.6 on the Noometry Index. Llama 4 Maverick costs 20× 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 Llama 4 Maverick?

Llama 4 Maverick is cheaper. It lists at $0.19 per million input tokens and $0.65 per million output tokens; Claude Sonnet 4.6 lists at $3 and $15.

Is Claude Sonnet 4.6 or Llama 4 Maverick better for coding?

Claude Sonnet 4.6 scores higher on coding benchmarks: 46.0 versus 26.3 in the Noometry coding category.

Which has the bigger context window?

Claude Sonnet 4.6 does, with 1M tokens against 128K.

How many benchmarks do Claude Sonnet 4.6 and Llama 4 Maverick share?

34 benchmarks have published results for both models. Claude Sonnet 4.6 has 57 scored results on Noometry and Llama 4 Maverick has 54.

Related comparisons

Go deeper