Noometry

Model comparison

Claude Sonnet 4 vs Qwen2.5-Coder-32B

Claude Sonnet 4 is the stronger model overall, scoring 40.8 to 33.4 on the Noometry Index. Qwen2.5-Coder-32B costs 8.1× less per token, which makes it the better buy when Claude Sonnet 4's lead doesn't matter for your workload.

Last verified . 15 shared benchmarks.

Claude Sonnet 4 Anthropic

40.8

Rank #145 Confirmed

Qwen2.5-Coder-32B Alibaba (Qwen)

33.4

Rank #245 Confirmed

Summary

  • They share 15 benchmarks with published results for both. Claude Sonnet 4 scores higher in 7 categories and Qwen2.5-Coder-32B in 1 category; 8 gaps are clear of the uncertainty.
  • The widest gap is in coding, where Claude Sonnet 4 leads 43.5 to 22.6.
  • The biggest single-benchmark swing is SWE-bench Verified (bash only): 64.9% for Claude Sonnet 4 and 9% for Qwen2.5-Coder-32B.
  • Qwen2.5-Coder-32B is cheaper at $0.66 / $1 per million input/output tokens, against $3 / $15 for Claude Sonnet 4.
  • Claude Sonnet 4 accepts more context: 200K tokens versus 33K.
  • Qwen2.5-Coder-32B has downloadable open weights; the other is API-only.

Side by side

Claude Sonnet 4Qwen2.5-Coder-32B
ProviderAnthropicAlibaba (Qwen)
Noometry Index40.833.4
Released2025-05-222024-09-18
WeightsProprietaryOpen
Context window200K33K
Max output64K29K
Input $ / M tokens$3$0.66
Output $ / M tokens$15$1
Results tracked5831

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), Qwen2.5-Coder-32B: 22.6 (#333)

BenchmarkClaude Sonnet 4Qwen2.5-Coder-32B
SWE-bench Verified (bash only)64.9%9%
Aider Polyglot61.3%16.4%
LMArena Coding14141276
SciCode40%—
GSO4.9%—
WeirdML46.1%—
BigCodeBench Instruct—49%
LiveBench Coding—56.9%
BigCodeBench Complete—58%
ALE-Bench655.35—
HumanEval+—87.2%
MBPP+—77%

Agentic & Tool Use Not comparable

Claude Sonnet 4: 38.5 (#31), Qwen2.5-Coder-32B: —

BenchmarkClaude Sonnet 4Qwen2.5-Coder-32B
TheAgentCompany33.1%—
Cybench35%—
DeepResearch Bench46.6%—
OSWorld43.9%—
METR Time Horizons62%—

Reasoning Claude Sonnet 4 leads

Claude Sonnet 4: 22.9 (#187), Qwen2.5-Coder-32B: 21.2 (#225)

BenchmarkClaude Sonnet 4Qwen2.5-Coder-32B
LMArena Hard Prompts13721251
Epoch Capabilities Index141.69119.49
ARC-AGI-25.9%—
SimpleBench45.5%—
Kagi LLM Benchmark73%—
ARC-AGI-140%—
CritPt0.3%—
EnigmaEval3.1%—
LiveBench Reasoning—42.1%
DTBench77.1%—
LiveBench Data Analysis—49.9%
LMCA29%—
ForecastBench60.2—
HellaSwag—83%
LiveBench—46.2%
WinoGrande—80.8%

Math Claude Sonnet 4 leads

Claude Sonnet 4: 43.3 (#80), Qwen2.5-Coder-32B: 33.3 (#204)

BenchmarkClaude Sonnet 4Qwen2.5-Coder-32B
LMArena Math13751251
OTIS Mock AIME 2024-202571.1%—
Omni-MATH60.2%—
LiveBench Math—46.6%
MATH Level 584.4%—
FrontierMath (Feb 2025 set)4.1%—
FrontierMath Tier 4 (v1)0%—
GSM8K—93%

Knowledge Claude Sonnet 4 leads

Claude Sonnet 4: 41.8 (#108), Qwen2.5-Coder-32B: 33.4 (#203)

BenchmarkClaude Sonnet 4Qwen2.5-Coder-32B
LMArena Expert13721221
GPQA Diamond79.2%—
Humanity's Last Exam7.8%—
MMLU-Pro84.3%—
Confabulations13.2%—
Vectara Hallucination Rate10.3%—
GPQA (HELM)70.6%—
ARC (AI2) Challenge—70.5%
MMLU—79.1%

Multimodal Not comparable

Claude Sonnet 4: 26.2 (#121), Qwen2.5-Coder-32B: —

BenchmarkClaude Sonnet 4Qwen2.5-Coder-32B
LMArena Vision1191—
GeoBench37%—
VPCT34%—
MindCube44.8%—

Multilingual Claude Sonnet 4 leads

Claude Sonnet 4: 46.7 (#156), Qwen2.5-Coder-32B: 37.8 (#235)

BenchmarkClaude Sonnet 4Qwen2.5-Coder-32B
LMArena Non-English13331205
LMArena Chinese13501222
LMArena Russian13551228
LMArena French1363—
LMArena German1331—
LMArena Japanese1302—
LMArena Korean1291—
LMArena Spanish1357—

Instruction Following Claude Sonnet 4 leads

Claude Sonnet 4: 71.7 (#145), Qwen2.5-Coder-32B: 61.4 (#245)

BenchmarkClaude Sonnet 4Qwen2.5-Coder-32B
LMArena Instruction Following13761223
LiveBench Instruction Following—58.7%
IFEval84%—

Long Context Qwen2.5-Coder-32B leads

Claude Sonnet 4: 33.7 (#259), Qwen2.5-Coder-32B: 38.0 (#208)

BenchmarkClaude Sonnet 4Qwen2.5-Coder-32B
LMArena Longer Query13981251
Fiction.LiveBench46.9%—

Writing & Preference Claude Sonnet 4 leads

Claude Sonnet 4: 57.1 (#132), Qwen2.5-Coder-32B: 41.6 (#240)

BenchmarkClaude Sonnet 4Qwen2.5-Coder-32B
LMArena Text13511230
LMArena Creative Writing13451174
LMArena Multi-Turn13761222
Short-Story Creative Writing81.4%—
EQ-Bench Creative Writing1483—
WildBench83.8%—
LiveBench Language—23.3%

Frequently asked questions

Is Claude Sonnet 4 better than Qwen2.5-Coder-32B?

Claude Sonnet 4 is the stronger model overall, scoring 40.8 to 33.4 on the Noometry Index. Qwen2.5-Coder-32B costs 8.1× 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 Qwen2.5-Coder-32B?

Qwen2.5-Coder-32B is cheaper. It lists at $0.66 per million input tokens and $1 per million output tokens; Claude Sonnet 4 lists at $3 and $15.

Is Claude Sonnet 4 or Qwen2.5-Coder-32B better for coding?

Claude Sonnet 4 scores higher on coding benchmarks: 43.5 versus 22.6 in the Noometry coding category.

Which has the bigger context window?

Claude Sonnet 4 does, with 200K tokens against 33K.

How many benchmarks do Claude Sonnet 4 and Qwen2.5-Coder-32B share?

15 benchmarks have published results for both models. Claude Sonnet 4 has 58 scored results on Noometry and Qwen2.5-Coder-32B has 31.

Related comparisons

Go deeper