Noometry

Model comparison

Grok 3 vs Qwen3-30B-A3B

Grok 3 is the stronger model overall, scoring 39.6 to 38.5 on the Noometry Index.

Last verified . 25 shared benchmarks.

Grok 3 xAI

39.6

Rank #150 Confirmed

Qwen3-30B-A3B Alibaba (Qwen)

38.5

Rank #174 Confirmed

Summary

  • They share 25 benchmarks with published results for both. Grok 3 scores higher in 8 categories and Qwen3-30B-A3B in 1 category; 6 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Qwen3-30B-A3B leads 21.6 to 13.8.
  • The biggest single-benchmark swing is Fiction.LiveBench: 58.3% for Grok 3 and 40.6% for Qwen3-30B-A3B.
  • Qwen3-30B-A3B has downloadable open weights; the other is API-only.

Side by side

Grok 3Qwen3-30B-A3B
ProviderxAIAlibaba (Qwen)
Noometry Index39.638.5
Released2025-04-092025-04-28
WeightsProprietaryOpen
Context window—41K
Max output—16K
Input $ / M tokens—$0.12
Output $ / M tokens—$0.50
Results tracked4032

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

Category by category

Coding Grok 3 leads

Grok 3: 41.5 (#113), Qwen3-30B-A3B: 37.0 (#188)

BenchmarkGrok 3Qwen3-30B-A3B
WeirdML37.2%29.8%
LMArena Coding14321416
Aider Polyglot53.3%—
SciCode—33.3%

Agentic & Tool Use Too close to call

Grok 3: 30.2 (#69), Qwen3-30B-A3B: 29.5 (#75)

BenchmarkGrok 3Qwen3-30B-A3B
Berkeley Function Calling Leaderboard—41.4%
BALROG29.5%—

Reasoning Qwen3-30B-A3B leads

Grok 3: 13.8 (#322), Qwen3-30B-A3B: 21.6 (#193)

BenchmarkGrok 3Qwen3-30B-A3B
Kagi LLM Benchmark61.3%54.9%
LMArena Hard Prompts14331398
Epoch Capabilities Index138.34139.63
ARC-AGI-20%—
SimpleBench36.1%—
ARC-AGI-15.5%—
CritPt—0.3%
Chess Puzzles—8%
DTBench—69.3%
LMCA—22.4%

Math Too close to call

Grok 3: 36.2 (#122), Qwen3-30B-A3B: 36.0 (#133)

BenchmarkGrok 3Qwen3-30B-A3B
OTIS Mock AIME 2024-202555.6%70.3%
LMArena Math13901394
MathArena Final-Answer Competitions—47.8%
Omni-MATH46.4%—
MATH Level 588.7%—
FrontierMath (Feb 2025 set)3.8%—
FrontierMath Tier 4 (v1)0%—

Knowledge Grok 3 leads

Grok 3: 46.0 (#76), Qwen3-30B-A3B: 41.7 (#96)

BenchmarkGrok 3Qwen3-30B-A3B
GPQA Diamond75.8%70.1%
Confabulations14.2%12.3%
LMArena Expert14201395
MMLU-Pro78.8%—
Vectara Hallucination Rate5.8%—
GPQA (HELM)65%—

Multilingual Grok 3 leads

Grok 3: 52.5 (#81), Qwen3-30B-A3B: 49.8 (#126)

BenchmarkGrok 3Qwen3-30B-A3B
LMArena Non-English14111372
LMArena Chinese14481434
LMArena French14601419
LMArena German14311379
LMArena Japanese13891338
LMArena Korean13741333
LMArena Russian14161369
LMArena Spanish14171403

Instruction Following Grok 3 leads

Grok 3: 75.2 (#69), Qwen3-30B-A3B: 72.2 (#137)

BenchmarkGrok 3Qwen3-30B-A3B
LMArena Instruction Following14091364
IFEval88.4%—

Long Context Grok 3 leads

Grok 3: 38.7 (#187), Qwen3-30B-A3B: 31.0 (#278)

BenchmarkGrok 3Qwen3-30B-A3B
Fiction.LiveBench58.3%40.6%
LMArena Longer Query14391379

Writing & Preference Too close to call

Grok 3: 56.0 (#136), Qwen3-30B-A3B: 55.9 (#138)

BenchmarkGrok 3Qwen3-30B-A3B
LMArena Text14261384
LMArena Creative Writing14141318
Short-Story Creative Writing76.4%75.3%
LMArena Multi-Turn14241378
EQ-Bench Creative Writing1186—
WildBench84.9%—

Frequently asked questions

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

Grok 3 is the stronger model overall, scoring 39.6 to 38.5 on the Noometry Index.

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

Grok 3 scores higher on coding benchmarks: 41.5 versus 37.0 in the Noometry coding category.

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

25 benchmarks have published results for both models. Grok 3 has 40 scored results on Noometry and Qwen3-30B-A3B has 32.

Related comparisons

Go deeper