Noometry

Model comparison

Claude Sonnet 4.6 vs Qwen3 235B-A22B

Claude Sonnet 4.6 is the stronger model overall, scoring 50.3 to 43.5 on the Noometry Index. Qwen3 235B-A22B costs 4.9× less per token, which makes it the better buy when Claude Sonnet 4.6's lead doesn't matter for your workload.

Last verified . 36 shared benchmarks.

Claude Sonnet 4.6 Anthropic

50.3

Rank #50 Confirmed

Qwen3 235B-A22B Alibaba (Qwen)

43.5

Rank #91 Confirmed

Summary

  • They share 36 benchmarks with published results for both. Claude Sonnet 4.6 scores higher in 8 categories and Qwen3 235B-A22B in 1 category; 8 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Claude Sonnet 4.6 leads 46.1 to 15.7.
  • The biggest single-benchmark swing is ARC-AGI-1: 86.5% for Claude Sonnet 4.6 and 11% for Qwen3 235B-A22B.
  • Qwen3 235B-A22B is cheaper at $0.70 / $2.80 per million input/output tokens, against $3 / $15 for Claude Sonnet 4.6.
  • Claude Sonnet 4.6 accepts more context: 1M tokens versus 131K.
  • Qwen3 235B-A22B has downloadable open weights; the other is API-only.

Side by side

Claude Sonnet 4.6Qwen3 235B-A22B
ProviderAnthropicAlibaba (Qwen)
Noometry Index50.343.5
Released2026-02-172025-04
WeightsProprietaryOpen
Context window1M131K
Max output128K16K
Input $ / M tokens$3$0.70
Output $ / M tokens$15$2.80
Results tracked5749

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 235B-A22B: 44.3 (#75)

BenchmarkClaude Sonnet 4.6Qwen3 235B-A22B
SciCode46.8%42.4%
WeirdML66.1%41%
LMArena Coding15041445
SWE-bench Verified75.2%—
DeepSWE29.9%—
FrontierCode24.3%—
Aider Polyglot—59.6%
LMArena WebDev1522—
ALE-Bench1,327—

Agentic & Tool Use Claude Sonnet 4.6 leads

Claude Sonnet 4.6: 39.1 (#28), Qwen3 235B-A22B: 33.9 (#51)

BenchmarkClaude Sonnet 4.6Qwen3 235B-A22B
Vending-Bench 27,204-11.34
Terminal-Bench53.4%—
APEX-Agents43%—
Berkeley Function Calling Leaderboard—52.1%
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 235B-A22B: 15.7 (#311)

BenchmarkClaude Sonnet 4.6Qwen3 235B-A22B
ARC-AGI-260.4%1.3%
ARC-AGI-186.5%11%
CritPt3.1%0%
Chess Puzzles13%12%
LMArena Hard Prompts14841433
Mystery Game Puzzles16%9%
DTBench89.9%80.3%
LMCA46.5%29.3%
Epoch Capabilities Index152.24143.85
ForecastBench6259.7
SimpleBench—31%
Kagi LLM Benchmark—69.4%
NYT Connections (extended)80.9%—
Thematic Generalization76.3%—

Math Claude Sonnet 4.6 leads

Claude Sonnet 4.6: 52.9 (#49), Qwen3 235B-A22B: 50.4 (#57)

BenchmarkClaude Sonnet 4.6Qwen3 235B-A22B
OTIS Mock AIME 2024-202585.8%86.7%
LMArena Math14621432
FrontierMath (Feb 2025 set)32.4%8.5%
FrontierMath Tier 4 (v1)8.3%0%
ProofBench45%—
Omni-MATH—71.8%
MATH Level 5—68.9%

Knowledge Claude Sonnet 4.6 leads

Claude Sonnet 4.6: 51.7 (#65), Qwen3 235B-A22B: 49.6 (#73)

BenchmarkClaude Sonnet 4.6Qwen3 235B-A22B
GPQA Diamond87.4%80.1%
SimpleQA Verified35.5%40.4%
Vectara Hallucination Rate10.6%9.3%
LMArena Expert15001463
MMLU-Pro—84.4%
Confabulations—15.6%
GPQA (HELM)—72.7%

Multimodal Not comparable

Claude Sonnet 4.6: 38.0 (#68), Qwen3 235B-A22B: —

BenchmarkClaude Sonnet 4.6Qwen3 235B-A22B
LMArena Vision1283—
Blueprint-Bench 26.7%—
LMArena Document1482—

Multilingual Claude Sonnet 4.6 leads

Claude Sonnet 4.6: 54.4 (#41), Qwen3 235B-A22B: 52.3 (#89)

BenchmarkClaude Sonnet 4.6Qwen3 235B-A22B
LMArena Non-English14401409
LMArena Chinese14911481
LMArena French14651445
LMArena German14281433
LMArena Japanese14201399
LMArena Korean14111391
LMArena Russian14401411
LMArena Spanish14641430

Instruction Following Claude Sonnet 4.6 leads

Claude Sonnet 4.6: 77.4 (#25), Qwen3 235B-A22B: 72.6 (#136)

BenchmarkClaude Sonnet 4.6Qwen3 235B-A22B
LMArena Instruction Following14751408
IFEval—83.5%

Long Context Too close to call

Claude Sonnet 4.6: 45.3 (#44), Qwen3 235B-A22B: 46.1 (#26)

BenchmarkClaude Sonnet 4.6Qwen3 235B-A22B
LMArena Longer Query14791426
Fiction.LiveBench—75%

Writing & Preference Claude Sonnet 4.6 leads

Claude Sonnet 4.6: 70.2 (#22), Qwen3 235B-A22B: 59.6 (#108)

BenchmarkClaude Sonnet 4.6Qwen3 235B-A22B
LMArena Text14581419
LMArena Creative Writing14351384
EQ-Bench Creative Writing18101366
LMArena Multi-Turn14641432
Short-Story Creative Writing—83%
WildBench—86.6%
EQ-Bench 41207—

Frequently asked questions

Is Claude Sonnet 4.6 better than Qwen3 235B-A22B?

Claude Sonnet 4.6 is the stronger model overall, scoring 50.3 to 43.5 on the Noometry Index. Qwen3 235B-A22B costs 4.9× 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 235B-A22B?

Qwen3 235B-A22B is cheaper. It lists at $0.70 per million input tokens and $2.80 per million output tokens; Claude Sonnet 4.6 lists at $3 and $15.

Is Claude Sonnet 4.6 or Qwen3 235B-A22B better for coding?

Claude Sonnet 4.6 scores higher on coding benchmarks: 46.3 versus 44.3 in the Noometry coding category.

Which has the bigger context window?

Claude Sonnet 4.6 does, with 1M tokens against 131K.

How many benchmarks do Claude Sonnet 4.6 and Qwen3 235B-A22B share?

36 benchmarks have published results for both models. Claude Sonnet 4.6 has 57 scored results on Noometry and Qwen3 235B-A22B has 49.

Related comparisons

Go deeper