Noometry

Model comparison

Claude Sonnet 4 vs Qwen3-Coder 480B-A35B Instruct

Claude Sonnet 4 is the stronger model overall, scoring 40.8 to 38.1 on the Noometry Index. Qwen3-Coder 480B-A35B Instruct costs 2.0× less per token, which makes it the better buy when Claude Sonnet 4's lead doesn't matter for your workload.

Last verified . 22 shared benchmarks.

Claude Sonnet 4 Anthropic

40.8

Rank #145 Confirmed

Qwen3-Coder 480B-A35B Instruct Alibaba (Qwen)

38.1

Rank #190 Confirmed

Summary

  • They share 22 benchmarks with published results for both. Claude Sonnet 4 scores higher in 6 categories and Qwen3-Coder 480B-A35B Instruct in 3 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in agentic & tool use, where Claude Sonnet 4 leads 38.5 to 23.9.
  • The biggest single-benchmark swing is Kagi LLM Benchmark: 73% for Claude Sonnet 4 and 49.5% for Qwen3-Coder 480B-A35B Instruct.
  • Qwen3-Coder 480B-A35B Instruct is cheaper at $1.50 / $7.50 per million input/output tokens, against $3 / $15 for Claude Sonnet 4.
  • Qwen3-Coder 480B-A35B Instruct accepts more context: 262K tokens versus 200K.
  • Qwen3-Coder 480B-A35B Instruct has downloadable open weights; the other is API-only.

Side by side

Claude Sonnet 4Qwen3-Coder 480B-A35B Instruct
ProviderAnthropicAlibaba (Qwen)
Noometry Index40.838.1
Released2025-05-222025-04
WeightsProprietaryOpen
Context window200K262K
Max output64K66K
Input $ / M tokens$3$1.50
Output $ / M tokens$15$7.50
Results tracked5825

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), Qwen3-Coder 480B-A35B Instruct: 35.5 (#223)

BenchmarkClaude Sonnet 4Qwen3-Coder 480B-A35B Instruct
SWE-bench Verified (bash only)64.9%55.4%
GSO4.9%4.9%
WeirdML46.1%41.2%
LMArena Coding14141412
ALE-Bench655.35461.45
Aider Polyglot61.3%—
LMArena WebDev—1275
SciCode40%—
AlgoTune—1.44

Agentic & Tool Use Claude Sonnet 4 leads

Claude Sonnet 4: 38.5 (#31), Qwen3-Coder 480B-A35B Instruct: 23.9 (#123)

BenchmarkClaude Sonnet 4Qwen3-Coder 480B-A35B Instruct
Terminal-Bench—27.2%
TheAgentCompany33.1%—
Cybench35%—
DeepResearch Bench46.6%—
OSWorld43.9%—
METR Time Horizons62%—

Reasoning Qwen3-Coder 480B-A35B Instruct leads

Claude Sonnet 4: 22.9 (#187), Qwen3-Coder 480B-A35B Instruct: 25.5 (#149)

BenchmarkClaude Sonnet 4Qwen3-Coder 480B-A35B Instruct
Kagi LLM Benchmark73%49.5%
LMArena Hard Prompts13721372
ARC-AGI-25.9%—
SimpleBench45.5%—
ARC-AGI-140%—
CritPt0.3%—
EnigmaEval3.1%—
DTBench77.1%—
LMCA29%—
Epoch Capabilities Index141.69—
ForecastBench60.2—

Math Claude Sonnet 4 leads

Claude Sonnet 4: 43.3 (#80), Qwen3-Coder 480B-A35B Instruct: 37.6 (#150)

BenchmarkClaude Sonnet 4Qwen3-Coder 480B-A35B Instruct
LMArena Math13751365
OTIS Mock AIME 2024-202571.1%—
Omni-MATH60.2%—
MATH Level 584.4%—
FrontierMath (Feb 2025 set)4.1%—
FrontierMath Tier 4 (v1)0%—

Knowledge Claude Sonnet 4 leads

Claude Sonnet 4: 41.8 (#108), Qwen3-Coder 480B-A35B Instruct: 37.0 (#162)

BenchmarkClaude Sonnet 4Qwen3-Coder 480B-A35B Instruct
LMArena Expert13721338
GPQA Diamond79.2%—
Humanity's Last Exam7.8%—
MMLU-Pro84.3%—
Confabulations13.2%—
Vectara Hallucination Rate10.3%—
GPQA (HELM)70.6%—

Multimodal Not comparable

Claude Sonnet 4: 26.2 (#121), Qwen3-Coder 480B-A35B Instruct: —

BenchmarkClaude Sonnet 4Qwen3-Coder 480B-A35B Instruct
LMArena Vision1191—
GeoBench37%—
VPCT34%—
MindCube44.8%—

Multilingual Too close to call

Claude Sonnet 4: 46.7 (#156), Qwen3-Coder 480B-A35B Instruct: 47.7 (#148)

BenchmarkClaude Sonnet 4Qwen3-Coder 480B-A35B Instruct
LMArena Non-English13331346
LMArena Chinese13501357
LMArena French13631398
LMArena German13311325
LMArena Japanese13021310
LMArena Korean12911305
LMArena Russian13551366
LMArena Spanish13571360

Instruction Following Too close to call

Claude Sonnet 4: 71.7 (#145), Qwen3-Coder 480B-A35B Instruct: 71.6 (#147)

BenchmarkClaude Sonnet 4Qwen3-Coder 480B-A35B Instruct
LMArena Instruction Following13761355
IFEval84%—

Long Context Qwen3-Coder 480B-A35B Instruct leads

Claude Sonnet 4: 33.7 (#259), Qwen3-Coder 480B-A35B Instruct: 42.0 (#131)

BenchmarkClaude Sonnet 4Qwen3-Coder 480B-A35B Instruct
LMArena Longer Query13981378
Fiction.LiveBench46.9%—

Writing & Preference Claude Sonnet 4 leads

Claude Sonnet 4: 57.1 (#132), Qwen3-Coder 480B-A35B Instruct: 55.3 (#147)

BenchmarkClaude Sonnet 4Qwen3-Coder 480B-A35B Instruct
LMArena Text13511357
LMArena Creative Writing13451333
LMArena Multi-Turn13761365
Short-Story Creative Writing81.4%—
EQ-Bench Creative Writing1483—
WildBench83.8%—

Frequently asked questions

Is Claude Sonnet 4 better than Qwen3-Coder 480B-A35B Instruct?

Claude Sonnet 4 is the stronger model overall, scoring 40.8 to 38.1 on the Noometry Index. Qwen3-Coder 480B-A35B Instruct costs 2.0× less per token, which makes it the better buy when Claude Sonnet 4's lead doesn't matter for your workload.

Which is cheaper, Claude Sonnet 4 or Qwen3-Coder 480B-A35B Instruct?

Qwen3-Coder 480B-A35B Instruct is cheaper. It lists at $1.50 per million input tokens and $7.50 per million output tokens; Claude Sonnet 4 lists at $3 and $15.

Is Claude Sonnet 4 or Qwen3-Coder 480B-A35B Instruct better for coding?

Claude Sonnet 4 scores higher on coding benchmarks: 43.5 versus 35.5 in the Noometry coding category.

Which has the bigger context window?

Qwen3-Coder 480B-A35B Instruct does, with 262K tokens against 200K.

How many benchmarks do Claude Sonnet 4 and Qwen3-Coder 480B-A35B Instruct share?

22 benchmarks have published results for both models. Claude Sonnet 4 has 58 scored results on Noometry and Qwen3-Coder 480B-A35B Instruct has 25.

Related comparisons

Go deeper