Noometry

Model comparison

Qwen3-30B-A3B vs Qwen3 32B

Qwen3-30B-A3B and Qwen3 32B score almost the same on the Noometry Index (38.9 vs 39.2), so choose on price, context window or the category you care about most.

Last verified . 24 shared benchmarks.

Qwen3-30B-A3B Alibaba (Qwen)

38.9

Rank #179 Confirmed

Qwen3 32B Alibaba (Qwen)

39.2

Rank #172 Confirmed

Summary

  • They share 24 benchmarks with published results for both. Qwen3-30B-A3B scores higher in 5 categories and Qwen3 32B in 4 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in long context, where Qwen3 32B leads 43.8 to 31.0.
  • The biggest single-benchmark swing is Fiction.LiveBench: 40.6% for Qwen3-30B-A3B and 74.2% for Qwen3 32B.
  • Qwen3-30B-A3B is cheaper at $0.12 / $0.50 per million input/output tokens, against $0.70 / $2.80 for Qwen3 32B.
  • Qwen3 32B accepts more context: 131K tokens versus 41K.

Side by side

Qwen3-30B-A3BQwen3 32B
ProviderAlibaba (Qwen)Alibaba (Qwen)
Noometry Index38.939.2
Released2025-04-282025-04
WeightsOpenOpen
Context window41K131K
Max output16K16K
Input $ / M tokens$0.12$0.70
Output $ / M tokens$0.50$2.80
Results tracked3226

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

Category by category

Coding Too close to call

Qwen3-30B-A3B: 37.5 (#194), Qwen3 32B: 37.7 (#190)

BenchmarkQwen3-30B-A3BQwen3 32B
SciCode33.3%35.4%
LMArena Coding14161358
Aider Polyglot—40%
WeirdML29.8%—

Agentic & Tool Use Qwen3 32B leads

Qwen3-30B-A3B: 29.8 (#82), Qwen3 32B: 32.6 (#62)

BenchmarkQwen3-30B-A3BQwen3 32B
Berkeley Function Calling Leaderboard41.4%48.7%

Reasoning Qwen3-30B-A3B leads

Qwen3-30B-A3B: 22.2 (#204), Qwen3 32B: 20.2 (#241)

BenchmarkQwen3-30B-A3BQwen3 32B
Kagi LLM Benchmark54.9%54.9%
CritPt0.3%0.3%
Chess Puzzles8%5%
LMArena Hard Prompts13981334
DTBench69.3%67.5%
LMCA22.4%17.3%
Epoch Capabilities Index139.63138.51

Math Qwen3 32B leads

Qwen3-30B-A3B: 37.4 (#157), Qwen3 32B: 39.7 (#99)

BenchmarkQwen3-30B-A3BQwen3 32B
OTIS Mock AIME 2024-202570.3%66.9%
LMArena Math13941399
MathArena Final-Answer Competitions47.8%—

Knowledge Qwen3-30B-A3B leads

Qwen3-30B-A3B: 41.8 (#105), Qwen3 32B: 40.0 (#125)

BenchmarkQwen3-30B-A3BQwen3 32B
GPQA Diamond70.1%65.7%
LMArena Expert13961362
Confabulations12.3%—
Vectara Hallucination Rate—5.9%

Multilingual Qwen3-30B-A3B leads

Qwen3-30B-A3B: 49.5 (#132), Qwen3 32B: 45.6 (#167)

BenchmarkQwen3-30B-A3BQwen3 32B
LMArena Non-English13721317
LMArena Chinese14331357
LMArena German13801341
LMArena Russian13701311
LMArena French1418—
LMArena Japanese1337—
LMArena Korean1331—
LMArena Spanish1404—

Instruction Following Qwen3-30B-A3B leads

Qwen3-30B-A3B: 72.0 (#142), Qwen3 32B: 68.9 (#179)

BenchmarkQwen3-30B-A3BQwen3 32B
LMArena Instruction Following13631305

Long Context Qwen3 32B leads

Qwen3-30B-A3B: 31.0 (#283), Qwen3 32B: 43.8 (#87)

BenchmarkQwen3-30B-A3BQwen3 32B
Fiction.LiveBench40.6%74.2%
LMArena Longer Query13791327

Writing & Preference Qwen3-30B-A3B leads

Qwen3-30B-A3B: 55.6 (#143), Qwen3 32B: 52.9 (#163)

BenchmarkQwen3-30B-A3BQwen3 32B
LMArena Text13841340
LMArena Creative Writing13171297
LMArena Multi-Turn13781331
Short-Story Creative Writing75.3%—

Frequently asked questions

Is Qwen3-30B-A3B better than Qwen3 32B?

Qwen3-30B-A3B and Qwen3 32B score almost the same on the Noometry Index (38.9 vs 39.2), so choose on price, context window or the category you care about most.

Which is cheaper, Qwen3-30B-A3B or Qwen3 32B?

Qwen3-30B-A3B is cheaper. It lists at $0.12 per million input tokens and $0.50 per million output tokens; Qwen3 32B lists at $0.70 and $2.80.

Is Qwen3-30B-A3B or Qwen3 32B better for coding?

They score almost the same on coding (37.5 vs 37.7); test both on your own repository before choosing.

Which has the bigger context window?

Qwen3 32B does, with 131K tokens against 41K.

How many benchmarks do Qwen3-30B-A3B and Qwen3 32B share?

24 benchmarks have published results for both models. Qwen3-30B-A3B has 32 scored results on Noometry and Qwen3 32B has 26.

Related comparisons

Go deeper