Noometry

Model comparison

Grok 3 vs Qwen3.5 35B-A3B

Qwen3.5 35B-A3B is the stronger model overall, scoring 41.7 to 39.6 on the Noometry Index.

Last verified . 21 shared benchmarks.

Grok 3 xAI

39.6

Rank #150 Confirmed

Qwen3.5 35B-A3B Alibaba (Qwen)

41.7

Rank #118 Confirmed

Summary

  • They share 21 benchmarks with published results for both. Grok 3 scores higher in 3 categories and Qwen3.5 35B-A3B in 5 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Qwen3.5 35B-A3B leads 23.9 to 13.8.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 55.6% for Grok 3 and 70% for Qwen3.5 35B-A3B.
  • Qwen3.5 35B-A3B has downloadable open weights; the other is API-only.

Side by side

Grok 3Qwen3.5 35B-A3B
ProviderxAIAlibaba (Qwen)
Noometry Index39.641.7
Released2025-04-092026-02-01
WeightsProprietaryOpen
Context window—262K
Max output—66K
Input $ / M tokens—$0.25
Output $ / M tokens—$2
Results tracked4028

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

Category by category

Coding Grok 3 leads

Grok 3: 41.5 (#113), Qwen3.5 35B-A3B: 33.5 (#244)

BenchmarkGrok 3Qwen3.5 35B-A3B
LMArena Coding14321410
Aider Polyglot53.3%—
LMArena WebDev—1254
SciCode—29.3%
WeirdML37.2%—

Agentic & Tool Use Not comparable

Grok 3: 30.2 (#69), Qwen3.5 35B-A3B: —

BenchmarkGrok 3Qwen3.5 35B-A3B
BALROG29.5%—

Reasoning Qwen3.5 35B-A3B leads

Grok 3: 13.8 (#322), Qwen3.5 35B-A3B: 23.9 (#158)

BenchmarkGrok 3Qwen3.5 35B-A3B
LMArena Hard Prompts14331400
Epoch Capabilities Index138.34142.52
ARC-AGI-20%—
SimpleBench36.1%—
Kagi LLM Benchmark61.3%—
ARC-AGI-15.5%—
CritPt—0.6%
Chess Puzzles—10%
DTBench—80%
LMCA—29.5%

Math Qwen3.5 35B-A3B leads

Grok 3: 36.2 (#122), Qwen3.5 35B-A3B: 38.4 (#86)

BenchmarkGrok 3Qwen3.5 35B-A3B
OTIS Mock AIME 2024-202555.6%70%
LMArena Math13901404
MathArena Final-Answer Competitions—56%
Omni-MATH46.4%—
MATH Level 588.7%—
FrontierMath (Feb 2025 set)3.8%—
FrontierMath Tier 4 (v1)0%—

Knowledge Qwen3.5 35B-A3B leads

Grok 3: 46.0 (#76), Qwen3.5 35B-A3B: 47.7 (#73)

BenchmarkGrok 3Qwen3.5 35B-A3B
GPQA Diamond75.8%83.5%
Vectara Hallucination Rate5.8%10.5%
LMArena Expert14201408
MMLU-Pro78.8%—
Confabulations14.2%—
GPQA (HELM)65%—

Multilingual Grok 3 leads

Grok 3: 52.5 (#81), Qwen3.5 35B-A3B: 50.2 (#122)

BenchmarkGrok 3Qwen3.5 35B-A3B
LMArena Non-English14111379
LMArena Chinese14481458
LMArena French14601412
LMArena German14311367
LMArena Japanese13891326
LMArena Korean13741354
LMArena Russian14161377
LMArena Spanish14171390

Instruction Following Grok 3 leads

Grok 3: 75.2 (#69), Qwen3.5 35B-A3B: 73.0 (#123)

BenchmarkGrok 3Qwen3.5 35B-A3B
LMArena Instruction Following14091379
IFEval88.4%—

Long Context Qwen3.5 35B-A3B leads

Grok 3: 38.7 (#187), Qwen3.5 35B-A3B: 42.4 (#122)

BenchmarkGrok 3Qwen3.5 35B-A3B
LMArena Longer Query14391390
Fiction.LiveBench58.3%—

Writing & Preference Qwen3.5 35B-A3B leads

Grok 3: 56.0 (#136), Qwen3.5 35B-A3B: 58.1 (#118)

BenchmarkGrok 3Qwen3.5 35B-A3B
LMArena Text14261395
LMArena Creative Writing14141347
LMArena Multi-Turn14241391
Short-Story Creative Writing76.4%—
EQ-Bench Creative Writing1186—
WildBench84.9%—

Frequently asked questions

Is Grok 3 better than Qwen3.5 35B-A3B?

Qwen3.5 35B-A3B is the stronger model overall, scoring 41.7 to 39.6 on the Noometry Index.

Is Grok 3 or Qwen3.5 35B-A3B better for coding?

Grok 3 scores higher on coding benchmarks: 41.5 versus 33.5 in the Noometry coding category.

How many benchmarks do Grok 3 and Qwen3.5 35B-A3B share?

21 benchmarks have published results for both models. Grok 3 has 40 scored results on Noometry and Qwen3.5 35B-A3B has 28.

Related comparisons

Go deeper