Noometry

Model comparison

Claude Sonnet 4.5 vs Qwen3 32B

Claude Sonnet 4.5 is the stronger model overall, scoring 44.0 to 38.8 on the Noometry Index. Qwen3 32B costs 4.9× less per token, which makes it the better buy when Claude Sonnet 4.5's lead doesn't matter for your workload.

Last verified . 24 shared benchmarks.

Claude Sonnet 4.5 Anthropic

44.0

Rank #76 Confirmed

Qwen3 32B Alibaba (Qwen)

38.8

Rank #166 Confirmed

Summary

  • They share 24 benchmarks with published results for both. Claude Sonnet 4.5 scores higher in 8 categories and Qwen3 32B in 1 category; 9 gaps are clear of the uncertainty.
  • The widest gap is in writing & preference, where Claude Sonnet 4.5 leads 66.7 to 53.1.
  • The biggest single-benchmark swing is Berkeley Function Calling Leaderboard: 73.2% for Claude Sonnet 4.5 and 48.7% for Qwen3 32B.
  • Qwen3 32B is cheaper at $0.70 / $2.80 per million input/output tokens, against $3 / $15 for Claude Sonnet 4.5.
  • Claude Sonnet 4.5 accepts more context: 1M tokens versus 131K.
  • Qwen3 32B has downloadable open weights; the other is API-only.

Side by side

Claude Sonnet 4.5Qwen3 32B
ProviderAnthropicAlibaba (Qwen)
Noometry Index44.038.8
Released2025-09-292025-04
WeightsProprietaryOpen
Context window1M131K
Max output64K16K
Input $ / M tokens$3$0.70
Output $ / M tokens$15$2.80
Results tracked7326

Sponsored placements are available on pages like this one. Advertise on Noometry

Category by category

Coding Claude Sonnet 4.5 leads

Claude Sonnet 4.5: 47.8 (#54), Qwen3 32B: 37.3 (#184)

BenchmarkClaude Sonnet 4.5Qwen3 32B
SciCode44.7%35.4%
LMArena Coding14891358
SWE-bench Verified71.3%—
SWE-bench Verified (bash only)71.4%—
Aider Polyglot—40%
LMArena WebDev1393—
SWE-bench Multilingual67%—
GSO14.7%—
WeirdML47.7%—
ALE-Bench796.15—
AlgoTune1.52—

Agentic & Tool Use Claude Sonnet 4.5 leads

Claude Sonnet 4.5: 38.1 (#30), Qwen3 32B: 32.3 (#58)

BenchmarkClaude Sonnet 4.5Qwen3 32B
Berkeley Function Calling Leaderboard73.2%48.7%
Terminal-Bench46.5%—
GDPval42.5%—
Remote Labor Index2.1%—
τ²-bench Airline72%—
τ²-bench Banking25.3%—
τ²-bench Retail72.4%—
τ²-bench Telecom84.9%—
Cybench60%—
DeepResearch Bench52.6%—
OSWorld62.9%—
LMArena Search1159—
METR Time Horizons67.4%—
Vending-Bench 23,839—

Reasoning Claude Sonnet 4.5 leads

Claude Sonnet 4.5: 26.9 (#113), Qwen3 32B: 19.6 (#233)

BenchmarkClaude Sonnet 4.5Qwen3 32B
Kagi LLM Benchmark57.9%54.9%
CritPt1.1%0.3%
Chess Puzzles12%5%
LMArena Hard Prompts14621335
DTBench83.2%67.5%
LMCA38.8%17.3%
Epoch Capabilities Index146.84138.51
ARC-AGI-213.6%—
SimpleBench54.3%—
NYT Connections (extended)37.3%—
ARC-AGI-163.7%—
EnigmaEval6%—
EBR-Bench2.4%—
Mystery Game Puzzles17%—
ForecastBench61.9—

Math Qwen3 32B leads

Claude Sonnet 4.5: 31.9 (#190), Qwen3 32B: 37.9 (#89)

BenchmarkClaude Sonnet 4.5Qwen3 32B
OTIS Mock AIME 2024-202577.8%66.9%
LMArena Math14481399
FrontierMath (Tiers 1-3)23.9%—
FrontierMath Tier 42.4%—
ProofBench19%—
Omni-MATH55.3%—
MATH Level 597.7%—
FrontierMath (Feb 2025 set)15.2%—
FrontierMath Tier 4 (v1)4.2%—

Knowledge Claude Sonnet 4.5 leads

Claude Sonnet 4.5: 48.4 (#70), Qwen3 32B: 40.0 (#112)

BenchmarkClaude Sonnet 4.5Qwen3 32B
GPQA Diamond82.3%65.7%
Vectara Hallucination Rate12%5.9%
LMArena Expert14831362
Humanity's Last Exam13.7%—
SimpleQA Verified30.7%—
MMLU-Pro86.9%—
GPQA (HELM)68.6%—

Multimodal Not comparable

Claude Sonnet 4.5: 34.1 (#84), Qwen3 32B: —

BenchmarkClaude Sonnet 4.5Qwen3 32B
VPCT39.8%—
LMArena Document1450—

Multilingual Claude Sonnet 4.5 leads

Claude Sonnet 4.5: 53.6 (#65), Qwen3 32B: 45.8 (#162)

BenchmarkClaude Sonnet 4.5Qwen3 32B
LMArena Non-English14251317
LMArena Chinese14591357
LMArena German14271341
LMArena Russian14361311
LMArena French1459—
LMArena Japanese1390—
LMArena Korean1403—
LMArena Spanish1457—

Instruction Following Claude Sonnet 4.5 leads

Claude Sonnet 4.5: 75.2 (#74), Qwen3 32B: 69.1 (#174)

BenchmarkClaude Sonnet 4.5Qwen3 32B
LMArena Instruction Following14591305
IFEval85%—

Long Context Claude Sonnet 4.5 leads

Claude Sonnet 4.5: 45.2 (#45), Qwen3 32B: 43.7 (#83)

BenchmarkClaude Sonnet 4.5Qwen3 32B
LMArena Longer Query14761327
Fiction.LiveBench—74.2%

Writing & Preference Claude Sonnet 4.5 leads

Claude Sonnet 4.5: 66.7 (#33), Qwen3 32B: 53.1 (#158)

BenchmarkClaude Sonnet 4.5Qwen3 32B
LMArena Text14391340
LMArena Creative Writing14421297
LMArena Multi-Turn14651331
EQ-Bench Creative Writing1678—
WildBench85.4%—

Frequently asked questions

Is Claude Sonnet 4.5 better than Qwen3 32B?

Claude Sonnet 4.5 is the stronger model overall, scoring 44.0 to 38.8 on the Noometry Index. Qwen3 32B costs 4.9× less per token, which makes it the better buy when Claude Sonnet 4.5's lead doesn't matter for your workload.

Which is cheaper, Claude Sonnet 4.5 or Qwen3 32B?

Qwen3 32B is cheaper. It lists at $0.70 per million input tokens and $2.80 per million output tokens; Claude Sonnet 4.5 lists at $3 and $15.

Is Claude Sonnet 4.5 or Qwen3 32B better for coding?

Claude Sonnet 4.5 scores higher on coding benchmarks: 47.8 versus 37.3 in the Noometry coding category.

Which has the bigger context window?

Claude Sonnet 4.5 does, with 1M tokens against 131K.

How many benchmarks do Claude Sonnet 4.5 and Qwen3 32B share?

24 benchmarks have published results for both models. Claude Sonnet 4.5 has 73 scored results on Noometry and Qwen3 32B has 26.

Related comparisons

Go deeper