Noometry

Model comparison

Grok-3 mini vs Qwen3.6 Max Preview

Qwen3.6 Max Preview is the stronger model overall, scoring 51.1 to 41.0 on the Noometry Index.

Last verified . 18 shared benchmarks.

Grok-3 mini xAI

41.0

Rank #130 Confirmed

Qwen3.6 Max Preview Alibaba (Qwen)

51.1

Rank #36 Confirmed

Summary

  • They share 18 benchmarks with published results for both. Grok-3 mini scores higher in 1 category and Qwen3.6 Max Preview in 7 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Qwen3.6 Max Preview leads 40.8 to 13.8.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 77.8% for Grok-3 mini and 91.1% for Qwen3.6 Max Preview.

Side by side

Grok-3 miniQwen3.6 Max Preview
ProviderxAIAlibaba (Qwen)
Noometry Index41.051.1
Released2025-04-092026-04-20
WeightsProprietaryProprietary
Context window—262K
Max output—66K
Input $ / M tokens—$1.30
Output $ / M tokens—$7.80
Results tracked3529

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

Category by category

Coding Qwen3.6 Max Preview leads

Grok-3 mini: 40.4 (#126), Qwen3.6 Max Preview: 48.6 (#50)

BenchmarkGrok-3 miniQwen3.6 Max Preview
LMArena Coding13801472
SWE-bench Verified—76.7%
Aider Polyglot49.3%—
LMArena WebDev—1482
WeirdML42.6%—

Agentic & Tool Use Not comparable

Grok-3 mini: —, Qwen3.6 Max Preview: —

BenchmarkGrok-3 miniQwen3.6 Max Preview
Vending-Bench 2—4,254

Reasoning Qwen3.6 Max Preview leads

Grok-3 mini: 13.8 (#323), Qwen3.6 Max Preview: 40.8 (#47)

BenchmarkGrok-3 miniQwen3.6 Max Preview
LMArena Hard Prompts13741457
Epoch Capabilities Index140.35149.27
ARC-AGI-20.4%—
SimpleBench—63%
Kagi LLM Benchmark61.3%—
NYT Connections (extended)—74.1%
ARC-AGI-116.5%—
Chess Puzzles—20%
Mystery Game Puzzles—19%
DTBench—87.2%
LMCA—42.5%

Math Qwen3.6 Max Preview leads

Grok-3 mini: 40.3 (#78), Qwen3.6 Max Preview: 52.2 (#40)

BenchmarkGrok-3 miniQwen3.6 Max Preview
OTIS Mock AIME 2024-202577.8%91.1%
LMArena Math13861465
FrontierMath (Feb 2025 set)5.9%23.1%
Omni-MATH31.8%—
MATH Level 590.9%—
FrontierMath Tier 4 (v1)—4.2%

Knowledge Qwen3.6 Max Preview leads

Grok-3 mini: 46.3 (#75), Qwen3.6 Max Preview: 57.6 (#35)

BenchmarkGrok-3 miniQwen3.6 Max Preview
GPQA Diamond76.3%87.4%
LMArena Expert13951476
SimpleQA Verified—52%
MMLU-Pro79.9%—
Confabulations10.8%—
GPQA (HELM)67.5%—

Multilingual Qwen3.6 Max Preview leads

Grok-3 mini: 48.3 (#141), Qwen3.6 Max Preview: 54.3 (#46)

BenchmarkGrok-3 miniQwen3.6 Max Preview
LMArena Non-English13521436
LMArena Chinese13871487
LMArena French13571449
LMArena Russian13521444
LMArena Spanish13791452
LMArena German1350—
LMArena Japanese1343—
LMArena Korean1336—

Instruction Following Grok-3 mini leads

Grok-3 mini: 78.7 (#8), Qwen3.6 Max Preview: 75.8 (#51)

BenchmarkGrok-3 miniQwen3.6 Max Preview
LMArena Instruction Following13561437
IFEval95.1%—

Long Context Qwen3.6 Max Preview leads

Grok-3 mini: 41.0 (#142), Qwen3.6 Max Preview: 44.6 (#59)

BenchmarkGrok-3 miniQwen3.6 Max Preview
LMArena Longer Query13721457
Fiction.LiveBench66.7%—

Writing & Preference Qwen3.6 Max Preview leads

Grok-3 mini: 52.7 (#163), Qwen3.6 Max Preview: 64.0 (#58)

BenchmarkGrok-3 miniQwen3.6 Max Preview
LMArena Text13701447
LMArena Creative Writing13421435
LMArena Multi-Turn13551456
Short-Story Creative Writing73.5%—
WildBench65.1%—

Frequently asked questions

Is Grok-3 mini better than Qwen3.6 Max Preview?

Qwen3.6 Max Preview is the stronger model overall, scoring 51.1 to 41.0 on the Noometry Index.

Is Grok-3 mini or Qwen3.6 Max Preview better for coding?

Qwen3.6 Max Preview scores higher on coding benchmarks: 48.6 versus 40.4 in the Noometry coding category.

How many benchmarks do Grok-3 mini and Qwen3.6 Max Preview share?

18 benchmarks have published results for both models. Grok-3 mini has 35 scored results on Noometry and Qwen3.6 Max Preview has 29.

Related comparisons

Go deeper