Noometry

Model comparison

Qwen3 14B vs Qwen3-30B-A3B

Qwen3-30B-A3B is the stronger model overall, scoring 38.9 to 35.5 on the Noometry Index.

Last verified . 11 shared benchmarks.

Qwen3 14B Alibaba (Qwen)

35.5

Rank #225 Confirmed

Qwen3-30B-A3B Alibaba (Qwen)

38.9

Rank #179 Confirmed

Summary

  • They share 11 benchmarks with published results for both. Qwen3 14B scores higher in 2 categories and Qwen3-30B-A3B in 4 categories; 4 gaps are clear of the uncertainty.
  • The widest gap is in long context, where Qwen3 14B leads 38.1 to 31.0.
  • The biggest single-benchmark swing is Fiction.LiveBench: 62.5% for Qwen3 14B and 40.6% for Qwen3-30B-A3B.
  • Qwen3-30B-A3B is cheaper at $0.12 / $0.50 per million input/output tokens, against $0.35 / $1.40 for Qwen3 14B.
  • Qwen3 14B accepts more context: 131K tokens versus 41K.

Side by side

Qwen3 14BQwen3-30B-A3B
ProviderAlibaba (Qwen)Alibaba (Qwen)
Noometry Index35.538.9
Released2025-042025-04-28
WeightsOpenOpen
Context window131K41K
Max output8K16K
Input $ / M tokens$0.35$0.12
Output $ / M tokens$1.40$0.50
Results tracked1232

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

Category by category

Coding Too close to call

Qwen3 14B: 37.3 (#195), Qwen3-30B-A3B: 37.5 (#194)

BenchmarkQwen3 14BQwen3-30B-A3B
SciCode31.6%33.3%
WeirdML—29.8%
LMArena Coding—1416

Agentic & Tool Use Too close to call

Qwen3 14B: 29.6 (#83), Qwen3-30B-A3B: 29.8 (#82)

BenchmarkQwen3 14BQwen3-30B-A3B
Berkeley Function Calling Leaderboard41%41.4%

Reasoning Qwen3-30B-A3B leads

Qwen3 14B: 18.5 (#280), Qwen3-30B-A3B: 22.2 (#204)

BenchmarkQwen3 14BQwen3-30B-A3B
Kagi LLM Benchmark49.1%54.9%
CritPt0%0.3%
Chess Puzzles4%8%
DTBench64%69.3%
LMCA18.2%22.4%
Epoch Capabilities Index138.23139.63
LMArena Hard Prompts—1398

Math Qwen3 14B leads

Qwen3 14B: 38.6 (#133), Qwen3-30B-A3B: 37.4 (#157)

BenchmarkQwen3 14BQwen3-30B-A3B
OTIS Mock AIME 2024-202566.4%70.3%
MathArena Final-Answer Competitions—47.8%
LMArena Math—1394

Knowledge Qwen3-30B-A3B leads

Qwen3 14B: 39.3 (#134), Qwen3-30B-A3B: 41.8 (#105)

BenchmarkQwen3 14BQwen3-30B-A3B
GPQA Diamond63.8%70.1%
Confabulations—12.3%
Vectara Hallucination Rate5.4%—
LMArena Expert—1396

Multilingual Not comparable

Qwen3 14B: —, Qwen3-30B-A3B: 49.5 (#132)

BenchmarkQwen3 14BQwen3-30B-A3B
LMArena Non-English—1372
LMArena Chinese—1433
LMArena French—1418
LMArena German—1380
LMArena Japanese—1337
LMArena Korean—1331
LMArena Russian—1370
LMArena Spanish—1404

Instruction Following Not comparable

Qwen3 14B: —, Qwen3-30B-A3B: 72.0 (#142)

BenchmarkQwen3 14BQwen3-30B-A3B
LMArena Instruction Following—1363

Long Context Qwen3 14B leads

Qwen3 14B: 38.1 (#204), Qwen3-30B-A3B: 31.0 (#283)

BenchmarkQwen3 14BQwen3-30B-A3B
Fiction.LiveBench62.5%40.6%
LMArena Longer Query—1379

Writing & Preference Not comparable

Qwen3 14B: —, Qwen3-30B-A3B: 55.6 (#143)

BenchmarkQwen3 14BQwen3-30B-A3B
LMArena Text—1384
LMArena Creative Writing—1317
Short-Story Creative Writing—75.3%
LMArena Multi-Turn—1378

Frequently asked questions

Is Qwen3 14B better than Qwen3-30B-A3B?

Qwen3-30B-A3B is the stronger model overall, scoring 38.9 to 35.5 on the Noometry Index.

Which is cheaper, Qwen3 14B or Qwen3-30B-A3B?

Qwen3-30B-A3B is cheaper. It lists at $0.12 per million input tokens and $0.50 per million output tokens; Qwen3 14B lists at $0.35 and $1.40.

Is Qwen3 14B or Qwen3-30B-A3B better for coding?

They score almost the same on coding (37.3 vs 37.5); test both on your own repository before choosing.

Which has the bigger context window?

Qwen3 14B does, with 131K tokens against 41K.

How many benchmarks do Qwen3 14B and Qwen3-30B-A3B share?

11 benchmarks have published results for both models. Qwen3 14B has 12 scored results on Noometry and Qwen3-30B-A3B has 32.

Related comparisons

Go deeper