Noometry

Model comparison

Qwen3-30B-A3B vs Qwen3 8B

Qwen3-30B-A3B is the stronger model overall, scoring 38.5 to 33.3 on the Noometry Index.

Last verified . 10 shared benchmarks.

Qwen3-30B-A3B Alibaba (Qwen)

38.5

Rank #174 Confirmed

Qwen3 8B Alibaba (Qwen)

33.3

Rank #237 Confirmed

Summary

  • They share 10 benchmarks with published results for both. Qwen3-30B-A3B scores higher in 4 categories and Qwen3 8B in 2 categories; 5 gaps are clear of the uncertainty.
  • The widest gap is in long context, where Qwen3 8B leads 37.8 to 31.0.
  • The biggest single-benchmark swing is Fiction.LiveBench: 40.6% for Qwen3-30B-A3B and 62.1% for Qwen3 8B.
  • Qwen3-30B-A3B is cheaper at $0.12 / $0.50 per million input/output tokens, against $0.18 / $0.70 for Qwen3 8B.
  • Qwen3 8B accepts more context: 131K tokens versus 41K.

Side by side

Qwen3-30B-A3BQwen3 8B
ProviderAlibaba (Qwen)Alibaba (Qwen)
Noometry Index38.533.3
Released2025-04-282025-04
WeightsOpenOpen
Context window41K131K
Max output16K8K
Input $ / M tokens$0.12$0.18
Output $ / M tokens$0.50$0.70
Results tracked3211

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

Category by category

Coding Qwen3-30B-A3B leads

Qwen3-30B-A3B: 37.0 (#188), Qwen3 8B: 33.4 (#245)

BenchmarkQwen3-30B-A3BQwen3 8B
SciCode33.3%22.6%
WeirdML29.8%—
LMArena Coding1416—

Agentic & Tool Use Too close to call

Qwen3-30B-A3B: 29.5 (#75), Qwen3 8B: 29.9 (#71)

BenchmarkQwen3-30B-A3BQwen3 8B
Berkeley Function Calling Leaderboard41.4%42.6%

Reasoning Qwen3-30B-A3B leads

Qwen3-30B-A3B: 21.6 (#193), Qwen3 8B: 16.1 (#299)

BenchmarkQwen3-30B-A3BQwen3 8B
CritPt0.3%0%
Chess Puzzles8%5%
DTBench69.3%59.7%
LMCA22.4%8.8%
Epoch Capabilities Index139.63136.17
Kagi LLM Benchmark54.9%—
LMArena Hard Prompts1398—

Math Qwen3-30B-A3B leads

Qwen3-30B-A3B: 36.0 (#133), Qwen3 8B: 33.3 (#176)

BenchmarkQwen3-30B-A3BQwen3 8B
OTIS Mock AIME 2024-202570.3%56.1%
MathArena Final-Answer Competitions47.8%—
LMArena Math1394—

Knowledge Qwen3-30B-A3B leads

Qwen3-30B-A3B: 41.7 (#96), Qwen3 8B: 36.1 (#164)

BenchmarkQwen3-30B-A3BQwen3 8B
GPQA Diamond70.1%56.8%
Confabulations12.3%—
Vectara Hallucination Rate—4.8%
LMArena Expert1395—

Multilingual Not comparable

Qwen3-30B-A3B: 49.8 (#126), Qwen3 8B: —

BenchmarkQwen3-30B-A3BQwen3 8B
LMArena Non-English1372—
LMArena Chinese1434—
LMArena French1419—
LMArena German1379—
LMArena Japanese1338—
LMArena Korean1333—
LMArena Russian1369—
LMArena Spanish1403—

Instruction Following Not comparable

Qwen3-30B-A3B: 72.2 (#137), Qwen3 8B: —

BenchmarkQwen3-30B-A3BQwen3 8B
LMArena Instruction Following1364—

Long Context Qwen3 8B leads

Qwen3-30B-A3B: 31.0 (#278), Qwen3 8B: 37.8 (#205)

BenchmarkQwen3-30B-A3BQwen3 8B
Fiction.LiveBench40.6%62.1%
LMArena Longer Query1379—

Writing & Preference Not comparable

Qwen3-30B-A3B: 55.9 (#138), Qwen3 8B: —

BenchmarkQwen3-30B-A3BQwen3 8B
LMArena Text1384—
LMArena Creative Writing1318—
Short-Story Creative Writing75.3%—
LMArena Multi-Turn1378—

Frequently asked questions

Is Qwen3-30B-A3B better than Qwen3 8B?

Qwen3-30B-A3B is the stronger model overall, scoring 38.5 to 33.3 on the Noometry Index.

Which is cheaper, Qwen3-30B-A3B or Qwen3 8B?

Qwen3-30B-A3B is cheaper. It lists at $0.12 per million input tokens and $0.50 per million output tokens; Qwen3 8B lists at $0.18 and $0.70.

Is Qwen3-30B-A3B or Qwen3 8B better for coding?

Qwen3-30B-A3B scores higher on coding benchmarks: 37.0 versus 33.4 in the Noometry coding category.

Which has the bigger context window?

Qwen3 8B does, with 131K tokens against 41K.

How many benchmarks do Qwen3-30B-A3B and Qwen3 8B share?

10 benchmarks have published results for both models. Qwen3-30B-A3B has 32 scored results on Noometry and Qwen3 8B has 11.

Related comparisons

Go deeper