Noometry

Model comparison

Grok 3 vs Qwen3 235B-A22B

Qwen3 235B-A22B is the stronger model overall, scoring 43.2 to 39.6 on the Noometry Index.

Last verified . 39 shared benchmarks.

Grok 3 xAI

39.6

Rank #150 Confirmed

Qwen3 235B-A22B Alibaba (Qwen)

43.2

Rank #83 Confirmed

Summary

  • They share 39 benchmarks with published results for both. Grok 3 scores higher in 2 categories 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 48.5 to 36.2.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 55.6% for Grok 3 and 86.7% for Qwen3 235B-A22B.
  • Qwen3 235B-A22B has downloadable open weights; the other is API-only.

Side by side

Grok 3Qwen3 235B-A22B
ProviderxAIAlibaba (Qwen)
Noometry Index39.643.2
Released2025-04-092025-04
WeightsProprietaryOpen
Context window—131K
Max output—16K
Input $ / M tokens—$0.70
Output $ / M tokens—$2.80
Results tracked4049

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

Category by category

Coding Qwen3 235B-A22B leads

Grok 3: 41.5 (#113), Qwen3 235B-A22B: 43.8 (#72)

BenchmarkGrok 3Qwen3 235B-A22B
Aider Polyglot53.3%59.6%
WeirdML37.2%41%
LMArena Coding14321445
SciCode—42.4%

Agentic & Tool Use Qwen3 235B-A22B leads

Grok 3: 30.2 (#69), Qwen3 235B-A22B: 33.7 (#48)

BenchmarkGrok 3Qwen3 235B-A22B
Berkeley Function Calling Leaderboard—52.1%
BALROG29.5%—
Vending-Bench 2—-11.34

Reasoning Qwen3 235B-A22B leads

Grok 3: 13.8 (#322), Qwen3 235B-A22B: 15.8 (#302)

BenchmarkGrok 3Qwen3 235B-A22B
ARC-AGI-20%1.3%
SimpleBench36.1%31%
Kagi LLM Benchmark61.3%69.4%
ARC-AGI-15.5%11%
LMArena Hard Prompts14331433
Epoch Capabilities Index138.34143.87
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: 36.2 (#122), Qwen3 235B-A22B: 48.5 (#51)

BenchmarkGrok 3Qwen3 235B-A22B
OTIS Mock AIME 2024-202555.6%86.7%
Omni-MATH46.4%71.8%
LMArena Math13901431
MATH Level 588.7%68.9%
FrontierMath (Feb 2025 set)3.8%8.5%
FrontierMath Tier 4 (v1)0%0%

Knowledge Qwen3 235B-A22B leads

Grok 3: 46.0 (#76), Qwen3 235B-A22B: 49.5 (#67)

BenchmarkGrok 3Qwen3 235B-A22B
GPQA Diamond75.8%80.1%
MMLU-Pro78.8%84.4%
Confabulations14.2%15.6%
Vectara Hallucination Rate5.8%9.3%
GPQA (HELM)65%72.7%
LMArena Expert14201460
SimpleQA Verified—40.4%

Multilingual Too close to call

Grok 3: 52.5 (#81), Qwen3 235B-A22B: 52.5 (#84)

BenchmarkGrok 3Qwen3 235B-A22B
LMArena Non-English14111410
LMArena Chinese14481481
LMArena French14601445
LMArena German14311432
LMArena Japanese13891400
LMArena Korean13741391
LMArena Russian14161411
LMArena Spanish14171429

Instruction Following Grok 3 leads

Grok 3: 75.2 (#69), Qwen3 235B-A22B: 72.8 (#132)

BenchmarkGrok 3Qwen3 235B-A22B
IFEval88.4%83.5%
LMArena Instruction Following14091408

Long Context Qwen3 235B-A22B leads

Grok 3: 38.7 (#187), Qwen3 235B-A22B: 46.1 (#25)

BenchmarkGrok 3Qwen3 235B-A22B
Fiction.LiveBench58.3%75%
LMArena Longer Query14391426

Writing & Preference Qwen3 235B-A22B leads

Grok 3: 56.0 (#136), Qwen3 235B-A22B: 59.8 (#103)

BenchmarkGrok 3Qwen3 235B-A22B
LMArena Text14261419
LMArena Creative Writing14141384
Short-Story Creative Writing76.4%83%
EQ-Bench Creative Writing11861366
WildBench84.9%86.6%
LMArena Multi-Turn14241432

Frequently asked questions

Is Grok 3 better than Qwen3 235B-A22B?

Qwen3 235B-A22B is the stronger model overall, scoring 43.2 to 39.6 on the Noometry Index.

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

Qwen3 235B-A22B scores higher on coding benchmarks: 43.8 versus 41.5 in the Noometry coding category.

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

39 benchmarks have published results for both models. Grok 3 has 40 scored results on Noometry and Qwen3 235B-A22B has 49.

Related comparisons

Go deeper