Noometry

Model comparison

Grok 4 vs Qwen3.5 122B-A10B

Grok 4 is the stronger model overall, scoring 48.1 to 42.1 on the Noometry Index.

Last verified . 18 shared benchmarks.

Grok 4 xAI

48.1

Rank #56 Confirmed

Qwen3.5 122B-A10B Alibaba (Qwen)

42.1

Rank #119 Confirmed

Summary

  • They share 18 benchmarks with published results for both. Grok 4 scores higher in 7 categories and Qwen3.5 122B-A10B in 2 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in long context, where Grok 4 leads 63.1 to 43.0.
  • Qwen3.5 122B-A10B has downloadable open weights; the other is API-only.

Side by side

Grok 4Qwen3.5 122B-A10B
ProviderxAIAlibaba (Qwen)
Noometry Index48.142.1
Released2025-07-092026-02-23
WeightsProprietaryOpen
Context window—262K
Max output—66K
Input $ / M tokens—$0.40
Output $ / M tokens—$3.20
Results tracked4827

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

Category by category

Coding Grok 4 leads

Grok 4: 50.3 (#46), Qwen3.5 122B-A10B: 39.1 (#162)

BenchmarkGrok 4Qwen3.5 122B-A10B
LMArena Coding14081436
Aider Polyglot79.6%—
LMArena WebDev—1360
SciCode—35.6%
WeirdML45.7%—

Agentic & Tool Use Not comparable

Grok 4: 32.3 (#68), Qwen3.5 122B-A10B: —

BenchmarkGrok 4Qwen3.5 122B-A10B
Terminal-Bench27.2%—
Berkeley Function Calling Leaderboard63%—
GDPval21.1%—
Cybench43%—
DeepResearch Bench47.3%—
BALROG43.6%—
LMArena Search1142—
METR Time Horizons66.6%—

Reasoning Grok 4 leads

Grok 4: 36.7 (#65), Qwen3.5 122B-A10B: 27.2 (#123)

BenchmarkGrok 4Qwen3.5 122B-A10B
LMArena Hard Prompts14091421
ARC-AGI-216%—
SimpleBench60.5%—
Kagi LLM Benchmark73.6%—
NYT Connections (extended)—51.7%
ARC-AGI-166.7%—
CritPt—0.9%
Chess Puzzles28%—
Thematic Generalization—51.2%
Mystery Game Puzzles—17%
DTBench—84.3%
LMCA—32.2%
Epoch Capabilities Index146.44—
ForecastBench60.9—

Math Grok 4 leads

Grok 4: 48.4 (#64), Qwen3.5 122B-A10B: 39.1 (#112)

BenchmarkGrok 4Qwen3.5 122B-A10B
LMArena Math14221432
OTIS Mock AIME 2024-202584%—
Omni-MATH60.3%—
FrontierMath (Feb 2025 set)19.7%—
FrontierMath Tier 4 (v1)2.1%—

Knowledge Grok 4 leads

Grok 4: 53.8 (#55), Qwen3.5 122B-A10B: 38.8 (#142)

BenchmarkGrok 4Qwen3.5 122B-A10B
LMArena Expert14151432
GPQA Diamond87%—
MMLU-Pro85.1%—
Confabulations12.4%—
Vectara Hallucination Rate—11.2%
GPQA (HELM)72.7%—

Multimodal Qwen3.5 122B-A10B leads

Grok 4: 33.7 (#94), Qwen3.5 122B-A10B: 39.6 (#57)

BenchmarkGrok 4Qwen3.5 122B-A10B
LMArena Vision12101245
GeoBench45%—

Multilingual Too close to call

Grok 4: 51.8 (#103), Qwen3.5 122B-A10B: 51.6 (#107)

BenchmarkGrok 4Qwen3.5 122B-A10B
LMArena Non-English14031400
LMArena Chinese14271462
LMArena French14181442
LMArena German14291426
LMArena Japanese13941367
LMArena Korean13771352
LMArena Russian14101400
LMArena Spanish14201424

Instruction Following Grok 4 leads

Grok 4: 79.2 (#5), Qwen3.5 122B-A10B: 73.8 (#115)

BenchmarkGrok 4Qwen3.5 122B-A10B
LMArena Instruction Following13871399
IFEval94.9%—

Long Context Grok 4 leads

Grok 4: 63.1 (#4), Qwen3.5 122B-A10B: 43.0 (#109)

BenchmarkGrok 4Qwen3.5 122B-A10B
LMArena Longer Query14091410
Fiction.LiveBench94.4%—

Writing & Preference Qwen3.5 122B-A10B leads

Grok 4: 58.5 (#116), Qwen3.5 122B-A10B: 60.0 (#105)

BenchmarkGrok 4Qwen3.5 122B-A10B
LMArena Text14111417
LMArena Creative Writing13971368
LMArena Multi-Turn14161416
Short-Story Creative Writing76.9%—
WildBench79.7%—

Frequently asked questions

Is Grok 4 better than Qwen3.5 122B-A10B?

Grok 4 is the stronger model overall, scoring 48.1 to 42.1 on the Noometry Index.

Is Grok 4 or Qwen3.5 122B-A10B better for coding?

Grok 4 scores higher on coding benchmarks: 50.3 versus 39.1 in the Noometry coding category.

How many benchmarks do Grok 4 and Qwen3.5 122B-A10B share?

18 benchmarks have published results for both models. Grok 4 has 48 scored results on Noometry and Qwen3.5 122B-A10B has 27.

Related comparisons

Go deeper