Noometry

Model comparison

GLM-4.5-Air vs Grok 4

Grok 4 is the stronger model overall, scoring 48.1 to 38.9 on the Noometry Index.

Last verified . 24 shared benchmarks.

GLM-4.5-Air Z.ai (Zhipu)

38.9

Rank #177 Confirmed

Grok 4 xAI

48.1

Rank #56 Confirmed

Summary

  • They share 24 benchmarks with published results for both. GLM-4.5-Air scores higher in 0 categories and Grok 4 in 8 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in long context, where Grok 4 leads 63.1 to 41.6.
  • The biggest single-benchmark swing is Kagi LLM Benchmark: 43% for GLM-4.5-Air and 73.6% for Grok 4.
  • GLM-4.5-Air has downloadable open weights; the other is API-only.

Side by side

GLM-4.5-AirGrok 4
ProviderZ.ai (Zhipu)xAI
Noometry Index38.948.1
Released2025-07-202025-07-09
WeightsOpenProprietary
Context window131K—
Max output98K—
Input $ / M tokens$0.20—
Output $ / M tokens$1.10—
Results tracked2748

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

Category by category

Coding Grok 4 leads

GLM-4.5-Air: 33.3 (#259), Grok 4: 50.3 (#46)

BenchmarkGLM-4.5-AirGrok 4
LMArena Coding13971408
Aider Polyglot—79.6%
GSO2.9%—
WeirdML—45.7%

Agentic & Tool Use Not comparable

GLM-4.5-Air: —, Grok 4: 32.3 (#68)

BenchmarkGLM-4.5-AirGrok 4
Terminal-Bench—27.2%
Berkeley Function Calling Leaderboard—63%
GDPval—21.1%
Cybench—43%
DeepResearch Bench—47.3%
BALROG—43.6%
LMArena Search—1142
METR Time Horizons—66.6%

Reasoning Grok 4 leads

GLM-4.5-Air: 24.1 (#166), Grok 4: 36.7 (#65)

BenchmarkGLM-4.5-AirGrok 4
Kagi LLM Benchmark43%73.6%
LMArena Hard Prompts13791409
ForecastBench59.260.9
ARC-AGI-2—16%
SimpleBench—60.5%
ARC-AGI-1—66.7%
Chess Puzzles—28%
Epoch Capabilities Index—146.44

Math Grok 4 leads

GLM-4.5-Air: 36.2 (#170), Grok 4: 48.4 (#64)

BenchmarkGLM-4.5-AirGrok 4
Omni-MATH39.1%60.3%
LMArena Math13961422
OTIS Mock AIME 2024-2025—84%
FrontierMath (Feb 2025 set)—19.7%
FrontierMath Tier 4 (v1)—2.1%

Knowledge Grok 4 leads

GLM-4.5-Air: 35.0 (#191), Grok 4: 53.8 (#55)

BenchmarkGLM-4.5-AirGrok 4
MMLU-Pro76.2%85.1%
GPQA (HELM)59.4%72.7%
LMArena Expert13701415
GPQA Diamond—87%
Humanity's Last Exam8.1%—
Confabulations—12.4%
Vectara Hallucination Rate9.3%—

Multimodal Not comparable

GLM-4.5-Air: —, Grok 4: 33.7 (#94)

BenchmarkGLM-4.5-AirGrok 4
LMArena Vision—1210
GeoBench—45%

Multilingual Grok 4 leads

GLM-4.5-Air: 49.1 (#135), Grok 4: 51.8 (#103)

BenchmarkGLM-4.5-AirGrok 4
LMArena Non-English13661403
LMArena Chinese14261427
LMArena French13991418
LMArena German13771429
LMArena Japanese13481394
LMArena Korean13081377
LMArena Russian13731410
LMArena Spanish13861420

Instruction Following Grok 4 leads

GLM-4.5-Air: 69.6 (#171), Grok 4: 79.2 (#5)

BenchmarkGLM-4.5-AirGrok 4
IFEval81.2%94.9%
LMArena Instruction Following13541387

Long Context Grok 4 leads

GLM-4.5-Air: 41.6 (#135), Grok 4: 63.1 (#4)

BenchmarkGLM-4.5-AirGrok 4
LMArena Longer Query13661409
Fiction.LiveBench—94.4%

Writing & Preference Grok 4 leads

GLM-4.5-Air: 55.9 (#139), Grok 4: 58.5 (#116)

BenchmarkGLM-4.5-AirGrok 4
LMArena Text13841411
LMArena Creative Writing13431397
WildBench78.9%79.7%
LMArena Multi-Turn13711416
Short-Story Creative Writing—76.9%

Frequently asked questions

Is GLM-4.5-Air better than Grok 4?

Grok 4 is the stronger model overall, scoring 48.1 to 38.9 on the Noometry Index.

Is GLM-4.5-Air or Grok 4 better for coding?

Grok 4 scores higher on coding benchmarks: 50.3 versus 33.3 in the Noometry coding category.

How many benchmarks do GLM-4.5-Air and Grok 4 share?

24 benchmarks have published results for both models. GLM-4.5-Air has 27 scored results on Noometry and Grok 4 has 48.

Related comparisons

Go deeper