Noometry

Model comparison

Grok-3 mini vs Qwen3-30B-A3B

Grok-3 mini is the stronger model overall, scoring 41.0 to 38.5 on the Noometry Index.

Last verified . 25 shared benchmarks.

Grok-3 mini xAI

41.0

Rank #130 Confirmed

Qwen3-30B-A3B Alibaba (Qwen)

38.5

Rank #174 Confirmed

Summary

  • They share 25 benchmarks with published results for both. Grok-3 mini scores higher in 5 categories and Qwen3-30B-A3B in 3 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in long context, where Grok-3 mini leads 41.0 to 31.0.
  • The biggest single-benchmark swing is Fiction.LiveBench: 66.7% for Grok-3 mini and 40.6% for Qwen3-30B-A3B.
  • Qwen3-30B-A3B has downloadable open weights; the other is API-only.

Side by side

Grok-3 miniQwen3-30B-A3B
ProviderxAIAlibaba (Qwen)
Noometry Index41.038.5
Released2025-04-092025-04-28
WeightsProprietaryOpen
Context window—41K
Max output—16K
Input $ / M tokens—$0.12
Output $ / M tokens—$0.50
Results tracked3532

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

Category by category

Coding Grok-3 mini leads

Grok-3 mini: 40.4 (#126), Qwen3-30B-A3B: 37.0 (#188)

BenchmarkGrok-3 miniQwen3-30B-A3B
WeirdML42.6%29.8%
LMArena Coding13801416
Aider Polyglot49.3%—
SciCode—33.3%

Agentic & Tool Use Not comparable

Grok-3 mini: —, Qwen3-30B-A3B: 29.5 (#75)

BenchmarkGrok-3 miniQwen3-30B-A3B
Berkeley Function Calling Leaderboard—41.4%

Reasoning Qwen3-30B-A3B leads

Grok-3 mini: 13.8 (#323), Qwen3-30B-A3B: 21.6 (#193)

BenchmarkGrok-3 miniQwen3-30B-A3B
Kagi LLM Benchmark61.3%54.9%
LMArena Hard Prompts13741398
Epoch Capabilities Index140.35139.63
ARC-AGI-20.4%—
ARC-AGI-116.5%—
CritPt—0.3%
Chess Puzzles—8%
DTBench—69.3%
LMCA—22.4%

Math Grok-3 mini leads

Grok-3 mini: 40.3 (#78), Qwen3-30B-A3B: 36.0 (#133)

BenchmarkGrok-3 miniQwen3-30B-A3B
OTIS Mock AIME 2024-202577.8%70.3%
LMArena Math13861394
MathArena Final-Answer Competitions—47.8%
Omni-MATH31.8%—
MATH Level 590.9%—
FrontierMath (Feb 2025 set)5.9%—

Knowledge Grok-3 mini leads

Grok-3 mini: 46.3 (#75), Qwen3-30B-A3B: 41.7 (#96)

BenchmarkGrok-3 miniQwen3-30B-A3B
GPQA Diamond76.3%70.1%
Confabulations10.8%12.3%
LMArena Expert13951395
MMLU-Pro79.9%—
GPQA (HELM)67.5%—

Multilingual Qwen3-30B-A3B leads

Grok-3 mini: 48.3 (#141), Qwen3-30B-A3B: 49.8 (#126)

BenchmarkGrok-3 miniQwen3-30B-A3B
LMArena Non-English13521372
LMArena Chinese13871434
LMArena French13571419
LMArena German13501379
LMArena Japanese13431338
LMArena Korean13361333
LMArena Russian13521369
LMArena Spanish13791403

Instruction Following Grok-3 mini leads

Grok-3 mini: 78.7 (#8), Qwen3-30B-A3B: 72.2 (#137)

BenchmarkGrok-3 miniQwen3-30B-A3B
LMArena Instruction Following13561364
IFEval95.1%—

Long Context Grok-3 mini leads

Grok-3 mini: 41.0 (#142), Qwen3-30B-A3B: 31.0 (#278)

BenchmarkGrok-3 miniQwen3-30B-A3B
Fiction.LiveBench66.7%40.6%
LMArena Longer Query13721379

Writing & Preference Qwen3-30B-A3B leads

Grok-3 mini: 52.7 (#163), Qwen3-30B-A3B: 55.9 (#138)

BenchmarkGrok-3 miniQwen3-30B-A3B
LMArena Text13701384
LMArena Creative Writing13421318
Short-Story Creative Writing73.5%75.3%
LMArena Multi-Turn13551378
WildBench65.1%—

Frequently asked questions

Is Grok-3 mini better than Qwen3-30B-A3B?

Grok-3 mini is the stronger model overall, scoring 41.0 to 38.5 on the Noometry Index.

Is Grok-3 mini or Qwen3-30B-A3B better for coding?

Grok-3 mini scores higher on coding benchmarks: 40.4 versus 37.0 in the Noometry coding category.

How many benchmarks do Grok-3 mini and Qwen3-30B-A3B share?

25 benchmarks have published results for both models. Grok-3 mini has 35 scored results on Noometry and Qwen3-30B-A3B has 32.

Related comparisons

Go deeper