Noometry

Model comparison

Claude 3 Sonnet vs Qwen3 32B

Qwen3 32B is the stronger model overall, scoring 39.2 to 29.0 on the Noometry Index.

Last verified . 17 shared benchmarks.

Claude 3 Sonnet Anthropic

29.0

Rank #319 Confirmed

Qwen3 32B Alibaba (Qwen)

39.2

Rank #172 Confirmed

Summary

  • They share 17 benchmarks with published results for both. Claude 3 Sonnet scores higher in 1 category and Qwen3 32B in 7 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in math, where Qwen3 32B leads 39.7 to 10.7.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 2.5% for Claude 3 Sonnet and 66.9% for Qwen3 32B.
  • Qwen3 32B has downloadable open weights; the other is API-only.

Side by side

Claude 3 SonnetQwen3 32B
ProviderAnthropicAlibaba (Qwen)
Noometry Index29.039.2
Released2024-02-292025-04
WeightsProprietaryOpen
Context window—131K
Max output—16K
Input $ / M tokens—$0.70
Output $ / M tokens—$2.80
Results tracked3026

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

Category by category

Coding Qwen3 32B leads

Claude 3 Sonnet: 29.6 (#302), Qwen3 32B: 37.7 (#190)

BenchmarkClaude 3 SonnetQwen3 32B
LMArena Coding12231358
Aider Polyglot—40%
SciCode—35.4%
WeirdML10.2%—
BigCodeBench Instruct42.7%—
BigCodeBench Complete53.8%—
HumanEval+64%—
MBPP+69.3%—

Agentic & Tool Use Not comparable

Claude 3 Sonnet: —, Qwen3 32B: 32.6 (#62)

BenchmarkClaude 3 SonnetQwen3 32B
Berkeley Function Calling Leaderboard—48.7%

Reasoning Too close to call

Claude 3 Sonnet: 20.5 (#237), Qwen3 32B: 20.2 (#241)

BenchmarkClaude 3 SonnetQwen3 32B
LMArena Hard Prompts11971334
DTBench53.6%67.5%
Epoch Capabilities Index120.7138.51
Kagi LLM Benchmark—54.9%
CritPt—0.3%
Chess Puzzles—5%
LMCA—17.3%
WinoGrande75.1%—

Math Qwen3 32B leads

Claude 3 Sonnet: 10.7 (#310), Qwen3 32B: 39.7 (#99)

BenchmarkClaude 3 SonnetQwen3 32B
OTIS Mock AIME 2024-20252.5%66.9%
LMArena Math12131399
MATH Level 518.2%—

Knowledge Qwen3 32B leads

Claude 3 Sonnet: 21.1 (#276), Qwen3 32B: 40.0 (#125)

BenchmarkClaude 3 SonnetQwen3 32B
GPQA Diamond40.6%65.7%
LMArena Expert11731362
Vectara Hallucination Rate—5.9%
MMLU75.9%—

Multimodal Not comparable

Claude 3 Sonnet: 25.2 (#125), Qwen3 32B: —

BenchmarkClaude 3 SonnetQwen3 32B
LMArena Vision984—

Multilingual Qwen3 32B leads

Claude 3 Sonnet: 37.8 (#234), Qwen3 32B: 45.6 (#167)

BenchmarkClaude 3 SonnetQwen3 32B
LMArena Non-English12051317
LMArena Chinese11891357
LMArena German12041341
LMArena Russian12271311
LMArena French1229—
LMArena Japanese1131—
LMArena Korean1128—
LMArena Spanish1204—

Instruction Following Qwen3 32B leads

Claude 3 Sonnet: 62.8 (#235), Qwen3 32B: 68.9 (#179)

BenchmarkClaude 3 SonnetQwen3 32B
LMArena Instruction Following11991305

Long Context Qwen3 32B leads

Claude 3 Sonnet: 36.7 (#228), Qwen3 32B: 43.8 (#87)

BenchmarkClaude 3 SonnetQwen3 32B
LMArena Longer Query12111327
Fiction.LiveBench—74.2%

Writing & Preference Qwen3 32B leads

Claude 3 Sonnet: 42.1 (#238), Qwen3 32B: 52.9 (#163)

BenchmarkClaude 3 SonnetQwen3 32B
LMArena Text12181340
LMArena Creative Writing11861297
LMArena Multi-Turn12271331

Frequently asked questions

Is Claude 3 Sonnet better than Qwen3 32B?

Qwen3 32B is the stronger model overall, scoring 39.2 to 29.0 on the Noometry Index.

Is Claude 3 Sonnet or Qwen3 32B better for coding?

Qwen3 32B scores higher on coding benchmarks: 37.7 versus 29.6 in the Noometry coding category.

How many benchmarks do Claude 3 Sonnet and Qwen3 32B share?

17 benchmarks have published results for both models. Claude 3 Sonnet has 30 scored results on Noometry and Qwen3 32B has 26.

Related comparisons

Go deeper