Noometry

Model comparison

Grok-3 mini vs Qwen3.6 35B-A3B

Grok-3 mini is the stronger model overall, scoring 41.2 to 37.6 on the Noometry Index.

Last verified . 4 shared benchmarks.

Grok-3 mini xAI

41.2

Rank #141 Confirmed

Qwen3.6 35B-A3B Alibaba (Qwen)

37.6

Rank #201 Confirmed

Summary

  • They share 4 benchmarks with published results for both. Grok-3 mini scores higher in 2 categories and Qwen3.6 35B-A3B in 2 categories; 4 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Qwen3.6 35B-A3B leads 28.0 to 13.6.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 77.8% for Grok-3 mini and 86.7% for Qwen3.6 35B-A3B.
  • Qwen3.6 35B-A3B has downloadable open weights; the other is API-only.

Side by side

Grok-3 miniQwen3.6 35B-A3B
ProviderxAIAlibaba (Qwen)
Noometry Index41.237.6
Released2025-04-092026-04-01
WeightsProprietaryOpen
Context window—262K
Max output—66K
Input $ / M tokens—$0.25
Output $ / M tokens—$1.49
Results tracked3514

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

Category by category

Coding Grok-3 mini leads

Grok-3 mini: 40.8 (#131), Qwen3.6 35B-A3B: 37.2 (#196)

BenchmarkGrok-3 miniQwen3.6 35B-A3B
WeirdML42.6%34.5%
Aider Polyglot49.3%—
SciCode—35.8%
LMArena Coding1379—

Agentic & Tool Use Not comparable

Grok-3 mini: —, Qwen3.6 35B-A3B: 22.1 (#134)

BenchmarkGrok-3 miniQwen3.6 35B-A3B
Terminal-Bench—23%

Reasoning Qwen3.6 35B-A3B leads

Grok-3 mini: 13.6 (#334), Qwen3.6 35B-A3B: 28.0 (#109)

BenchmarkGrok-3 miniQwen3.6 35B-A3B
Epoch Capabilities Index140.35143.93
ARC-AGI-20.4%—
Kagi LLM Benchmark61.3%—
NYT Connections (extended)—41.6%
ARC-AGI-116.5%—
CritPt—0.3%
Chess Puzzles—26%
LMArena Hard Prompts1375—
Mystery Game Puzzles—22%
DTBench—73.9%
LMCA—29.7%
Surface Evolver Bench—44.4%

Math Grok-3 mini leads

Grok-3 mini: 42.1 (#85), Qwen3.6 35B-A3B: 38.9 (#121)

BenchmarkGrok-3 miniQwen3.6 35B-A3B
OTIS Mock AIME 2024-202577.8%86.7%
FrontierMath (Tiers 1-3)—20.4%
Omni-MATH31.8%—
LMArena Math1386—
MATH Level 590.9%—
FrontierMath (Feb 2025 set)5.9%—

Knowledge Qwen3.6 35B-A3B leads

Grok-3 mini: 46.4 (#81), Qwen3.6 35B-A3B: 51.3 (#68)

BenchmarkGrok-3 miniQwen3.6 35B-A3B
GPQA Diamond76.3%84.8%
MMLU-Pro79.9%—
Confabulations10.8%—
GPQA (HELM)67.5%—
LMArena Expert1395—

Multilingual Not comparable

Grok-3 mini: 48.1 (#145), Qwen3.6 35B-A3B: —

BenchmarkGrok-3 miniQwen3.6 35B-A3B
LMArena Non-English1352—
LMArena Chinese1387—
LMArena French1357—
LMArena German1349—
LMArena Japanese1342—
LMArena Korean1335—
LMArena Russian1353—
LMArena Spanish1381—

Instruction Following Not comparable

Grok-3 mini: 78.5 (#9), Qwen3.6 35B-A3B: —

BenchmarkGrok-3 miniQwen3.6 35B-A3B
IFEval95.1%—
LMArena Instruction Following1357—

Long Context Not comparable

Grok-3 mini: 41.0 (#147), Qwen3.6 35B-A3B: —

BenchmarkGrok-3 miniQwen3.6 35B-A3B
Fiction.LiveBench66.7%—
LMArena Longer Query1372—

Writing & Preference Not comparable

Grok-3 mini: 52.5 (#169), Qwen3.6 35B-A3B: —

BenchmarkGrok-3 miniQwen3.6 35B-A3B
LMArena Text1370—
LMArena Creative Writing1342—
Short-Story Creative Writing73.5%—
WildBench65.1%—
LMArena Multi-Turn1355—

Frequently asked questions

Is Grok-3 mini better than Qwen3.6 35B-A3B?

Grok-3 mini is the stronger model overall, scoring 41.2 to 37.6 on the Noometry Index.

Is Grok-3 mini or Qwen3.6 35B-A3B better for coding?

Grok-3 mini scores higher on coding benchmarks: 40.8 versus 37.2 in the Noometry coding category.

How many benchmarks do Grok-3 mini and Qwen3.6 35B-A3B share?

4 benchmarks have published results for both models. Grok-3 mini has 35 scored results on Noometry and Qwen3.6 35B-A3B has 14.

Related comparisons

Go deeper