Noometry

Model comparison

Claude Sonnet 4.6 vs Qwen3 Max

Claude Sonnet 4.6 is the stronger model overall, scoring 50.3 to 43.7 on the Noometry Index. Qwen3 Max costs 2.5× less per token, which makes it the better buy when Claude Sonnet 4.6's lead doesn't matter for your workload.

Last verified . 28 shared benchmarks.

Claude Sonnet 4.6 Anthropic

50.3

Rank #50 Confirmed

Qwen3 Max Alibaba (Qwen)

43.7

Rank #87 Confirmed

Summary

  • They share 28 benchmarks with published results for both. Claude Sonnet 4.6 scores higher in 8 categories and Qwen3 Max in 0 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Claude Sonnet 4.6 leads 46.1 to 22.6.
  • The biggest single-benchmark swing is NYT Connections (extended): 80.9% for Claude Sonnet 4.6 and 30.1% for Qwen3 Max.
  • Qwen3 Max is cheaper at $1.20 / $6 per million input/output tokens, against $3 / $15 for Claude Sonnet 4.6.
  • Claude Sonnet 4.6 accepts more context: 1M tokens versus 262K.

Side by side

Claude Sonnet 4.6Qwen3 Max
ProviderAnthropicAlibaba (Qwen)
Noometry Index50.343.7
Released2026-02-172025-09-23
WeightsProprietaryProprietary
Context window1M262K
Max output128K66K
Input $ / M tokens$3$1.20
Output $ / M tokens$15$6
Results tracked5733

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), Qwen3 Max: 43.0 (#93)

BenchmarkClaude Sonnet 4.6Qwen3 Max
LMArena Coding15041456
ALE-Bench1,327370.45
SWE-bench Verified75.2%—
DeepSWE29.9%—
FrontierCode24.3%—
LMArena WebDev1522—
SciCode46.8%—
WeirdML66.1%—

Agentic & Tool Use Not comparable

Claude Sonnet 4.6: 39.1 (#28), Qwen3 Max: —

BenchmarkClaude Sonnet 4.6Qwen3 Max
Vending-Bench 27,20471.56
Terminal-Bench53.4%—
APEX-Agents43%—
OSWorld 2.09.3%—
DeepResearch Bench54.9%—
OSWorld72.1%—
ExploitBench23.6%—
GBAEval48.8%—
GDP.pdf18%—
LMArena Search1221—

Reasoning Claude Sonnet 4.6 leads

Claude Sonnet 4.6: 46.1 (#45), Qwen3 Max: 22.6 (#190)

BenchmarkClaude Sonnet 4.6Qwen3 Max
NYT Connections (extended)80.9%30.1%
Chess Puzzles13%4%
LMArena Hard Prompts14841448
Mystery Game Puzzles16%5%
DTBench89.9%82.1%
LMCA46.5%28.3%
Epoch Capabilities Index152.24142.38
ARC-AGI-260.4%—
Kagi LLM Benchmark—72.5%
ARC-AGI-186.5%—
CritPt3.1%—
Thematic Generalization76.3%—
ForecastBench62—

Math Claude Sonnet 4.6 leads

Claude Sonnet 4.6: 52.9 (#49), Qwen3 Max: 38.7 (#131)

BenchmarkClaude Sonnet 4.6Qwen3 Max
OTIS Mock AIME 2024-202585.8%73.3%
LMArena Math14621446
FrontierMath (Tiers 1-3)—18.9%
ProofBench45%—
MATH Level 5—97.1%
FrontierMath (Feb 2025 set)32.4%—
FrontierMath Tier 4 (v1)8.3%—

Knowledge Claude Sonnet 4.6 leads

Claude Sonnet 4.6: 51.7 (#65), Qwen3 Max: 48.1 (#78)

BenchmarkClaude Sonnet 4.6Qwen3 Max
GPQA Diamond87.4%72.6%
SimpleQA Verified35.5%48.7%
LMArena Expert15001455
Vectara Hallucination Rate10.6%—

Multimodal Not comparable

Claude Sonnet 4.6: 38.0 (#68), Qwen3 Max: —

BenchmarkClaude Sonnet 4.6Qwen3 Max
LMArena Vision1283—
Blueprint-Bench 26.7%—
LMArena Document1482—

Multilingual Too close to call

Claude Sonnet 4.6: 54.4 (#41), Qwen3 Max: 53.7 (#62)

BenchmarkClaude Sonnet 4.6Qwen3 Max
LMArena Non-English14401429
LMArena Chinese14911478
LMArena French14651449
LMArena German14281463
LMArena Japanese14201397
LMArena Korean14111399
LMArena Russian14401428
LMArena Spanish14641462

Instruction Following Claude Sonnet 4.6 leads

Claude Sonnet 4.6: 77.4 (#25), Qwen3 Max: 74.8 (#87)

BenchmarkClaude Sonnet 4.6Qwen3 Max
LMArena Instruction Following14751419

Long Context Claude Sonnet 4.6 leads

Claude Sonnet 4.6: 45.3 (#44), Qwen3 Max: 41.6 (#134)

BenchmarkClaude Sonnet 4.6Qwen3 Max
LMArena Longer Query14791438
Fiction.LiveBench—66.7%
CL-bench—14.5%

Writing & Preference Claude Sonnet 4.6 leads

Claude Sonnet 4.6: 70.2 (#22), Qwen3 Max: 62.4 (#76)

BenchmarkClaude Sonnet 4.6Qwen3 Max
LMArena Text14581439
LMArena Creative Writing14351402
LMArena Multi-Turn14641446
EQ-Bench Creative Writing1810—
EQ-Bench 41207—

Frequently asked questions

Is Claude Sonnet 4.6 better than Qwen3 Max?

Claude Sonnet 4.6 is the stronger model overall, scoring 50.3 to 43.7 on the Noometry Index. Qwen3 Max costs 2.5× 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 Qwen3 Max?

Qwen3 Max is cheaper. It lists at $1.20 per million input tokens and $6 per million output tokens; Claude Sonnet 4.6 lists at $3 and $15.

Is Claude Sonnet 4.6 or Qwen3 Max better for coding?

Claude Sonnet 4.6 scores higher on coding benchmarks: 46.3 versus 43.0 in the Noometry coding category.

Which has the bigger context window?

Claude Sonnet 4.6 does, with 1M tokens against 262K.

How many benchmarks do Claude Sonnet 4.6 and Qwen3 Max share?

28 benchmarks have published results for both models. Claude Sonnet 4.6 has 57 scored results on Noometry and Qwen3 Max has 33.

Related comparisons

Go deeper