Noometry

Model comparison

Grok-3 mini vs Qwen3 235B-A22B

Qwen3 235B-A22B is the stronger model overall, scoring 43.5 to 41.2 on the Noometry Index.

Last verified . 35 shared benchmarks.

Grok-3 mini xAI

41.2

Rank #141 Confirmed

Qwen3 235B-A22B Alibaba (Qwen)

43.5

Rank #91 Confirmed

Summary

  • They share 35 benchmarks with published results for both. Grok-3 mini scores higher in 1 category and Qwen3 235B-A22B in 7 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in math, where Qwen3 235B-A22B leads 50.4 to 42.1.
  • The biggest single-benchmark swing is Omni-MATH: 31.8% for Grok-3 mini and 71.8% for Qwen3 235B-A22B.
  • Qwen3 235B-A22B has downloadable open weights; the other is API-only.

Side by side

Grok-3 miniQwen3 235B-A22B
ProviderxAIAlibaba (Qwen)
Noometry Index41.243.5
Released2025-04-092025-04
WeightsProprietaryOpen
Context window—131K
Max output—16K
Input $ / M tokens—$0.70
Output $ / M tokens—$2.80
Results tracked3549

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

Category by category

Coding Qwen3 235B-A22B leads

Grok-3 mini: 40.8 (#131), Qwen3 235B-A22B: 44.3 (#75)

BenchmarkGrok-3 miniQwen3 235B-A22B
Aider Polyglot49.3%59.6%
WeirdML42.6%41%
LMArena Coding13791445
SciCode—42.4%

Agentic & Tool Use Not comparable

Grok-3 mini: —, Qwen3 235B-A22B: 33.9 (#51)

BenchmarkGrok-3 miniQwen3 235B-A22B
Berkeley Function Calling Leaderboard—52.1%
Vending-Bench 2—-11.34

Reasoning Qwen3 235B-A22B leads

Grok-3 mini: 13.6 (#334), Qwen3 235B-A22B: 15.7 (#311)

BenchmarkGrok-3 miniQwen3 235B-A22B
ARC-AGI-20.4%1.3%
Kagi LLM Benchmark61.3%69.4%
ARC-AGI-116.5%11%
LMArena Hard Prompts13751433
Epoch Capabilities Index140.35143.85
SimpleBench—31%
CritPt—0%
Chess Puzzles—12%
Mystery Game Puzzles—9%
DTBench—80.3%
LMCA—29.3%
ForecastBench—59.7

Math Qwen3 235B-A22B leads

Grok-3 mini: 42.1 (#85), Qwen3 235B-A22B: 50.4 (#57)

BenchmarkGrok-3 miniQwen3 235B-A22B
OTIS Mock AIME 2024-202577.8%86.7%
Omni-MATH31.8%71.8%
LMArena Math13861432
MATH Level 590.9%68.9%
FrontierMath (Feb 2025 set)5.9%8.5%
FrontierMath Tier 4 (v1)—0%

Knowledge Qwen3 235B-A22B leads

Grok-3 mini: 46.4 (#81), Qwen3 235B-A22B: 49.6 (#73)

BenchmarkGrok-3 miniQwen3 235B-A22B
GPQA Diamond76.3%80.1%
MMLU-Pro79.9%84.4%
Confabulations10.8%15.6%
GPQA (HELM)67.5%72.7%
LMArena Expert13951463
SimpleQA Verified—40.4%
Vectara Hallucination Rate—9.3%

Multilingual Qwen3 235B-A22B leads

Grok-3 mini: 48.1 (#145), Qwen3 235B-A22B: 52.3 (#89)

BenchmarkGrok-3 miniQwen3 235B-A22B
LMArena Non-English13521409
LMArena Chinese13871481
LMArena French13571445
LMArena German13491433
LMArena Japanese13421399
LMArena Korean13351391
LMArena Russian13531411
LMArena Spanish13811430

Instruction Following Grok-3 mini leads

Grok-3 mini: 78.5 (#9), Qwen3 235B-A22B: 72.6 (#136)

BenchmarkGrok-3 miniQwen3 235B-A22B
IFEval95.1%83.5%
LMArena Instruction Following13571408

Long Context Qwen3 235B-A22B leads

Grok-3 mini: 41.0 (#147), Qwen3 235B-A22B: 46.1 (#26)

BenchmarkGrok-3 miniQwen3 235B-A22B
Fiction.LiveBench66.7%75%
LMArena Longer Query13721426

Writing & Preference Qwen3 235B-A22B leads

Grok-3 mini: 52.5 (#169), Qwen3 235B-A22B: 59.6 (#108)

BenchmarkGrok-3 miniQwen3 235B-A22B
LMArena Text13701419
LMArena Creative Writing13421384
Short-Story Creative Writing73.5%83%
WildBench65.1%86.6%
LMArena Multi-Turn13551432
EQ-Bench Creative Writing—1366

Frequently asked questions

Is Grok-3 mini better than Qwen3 235B-A22B?

Qwen3 235B-A22B is the stronger model overall, scoring 43.5 to 41.2 on the Noometry Index.

Is Grok-3 mini or Qwen3 235B-A22B better for coding?

Qwen3 235B-A22B scores higher on coding benchmarks: 44.3 versus 40.8 in the Noometry coding category.

How many benchmarks do Grok-3 mini and Qwen3 235B-A22B share?

35 benchmarks have published results for both models. Grok-3 mini has 35 scored results on Noometry and Qwen3 235B-A22B has 49.

Related comparisons

Go deeper