Noometry

Model comparison

GLM-4.6 vs Grok 4

Grok 4 is the stronger model overall, scoring 48.1 to 41.4 on the Noometry Index.

Last verified . 22 shared benchmarks.

GLM-4.6 Z.ai (Zhipu)

41.4

Rank #135 Confirmed

Grok 4 xAI

48.1

Rank #56 Confirmed

Summary

  • They share 22 benchmarks with published results for both. GLM-4.6 scores higher in 3 categories and Grok 4 in 6 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in long context, where Grok 4 leads 63.1 to 43.4.
  • The biggest single-benchmark swing is Kagi LLM Benchmark: 47.4% for GLM-4.6 and 73.6% for Grok 4.
  • GLM-4.6 has downloadable open weights; the other is API-only.

Side by side

GLM-4.6Grok 4
ProviderZ.ai (Zhipu)xAI
Noometry Index41.448.1
Released2025-09-302025-07-09
WeightsOpenProprietary
Context window205K—
Max output131K—
Input $ / M tokens$0.60—
Output $ / M tokens$2.20—
Results tracked2948

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

Category by category

Coding Grok 4 leads

GLM-4.6: 40.1 (#148), Grok 4: 50.3 (#46)

BenchmarkGLM-4.6Grok 4
LMArena Coding14491408
SWE-bench Verified (bash only)55.4%—
Aider Polyglot—79.6%
LMArena WebDev1340—
SciCode38.4%—
WeirdML—45.7%
ALE-Bench340.82—

Agentic & Tool Use Too close to call

GLM-4.6: 32.3 (#66), Grok 4: 32.3 (#68)

BenchmarkGLM-4.6Grok 4
Terminal-Bench24.5%27.2%
Berkeley Function Calling Leaderboard72.4%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-4.6: 23.7 (#172), Grok 4: 36.7 (#65)

BenchmarkGLM-4.6Grok 4
Kagi LLM Benchmark47.4%73.6%
LMArena Hard Prompts14401409
ARC-AGI-2—16%
SimpleBench—60.5%
ARC-AGI-1—66.7%
CritPt1.1%—
Chess Puzzles—28%
Epoch Capabilities Index—146.44
ForecastBench—60.9

Math Grok 4 leads

GLM-4.6: 39.1 (#111), Grok 4: 48.4 (#64)

BenchmarkGLM-4.6Grok 4
LMArena Math14321422
FrontierMath (Feb 2025 set)3.8%19.7%
FrontierMath Tier 4 (v1)2.1%2.1%
OTIS Mock AIME 2024-2025—84%
Omni-MATH—60.3%

Knowledge Grok 4 leads

GLM-4.6: 40.2 (#124), Grok 4: 53.8 (#55)

BenchmarkGLM-4.6Grok 4
LMArena Expert14311415
GPQA Diamond—87%
MMLU-Pro—85.1%
Confabulations—12.4%
Vectara Hallucination Rate9.5%—
GPQA (HELM)—72.7%

Multimodal Not comparable

GLM-4.6: —, Grok 4: 33.7 (#94)

BenchmarkGLM-4.6Grok 4
LMArena Vision—1210
GeoBench—45%

Multilingual GLM-4.6 leads

GLM-4.6: 53.5 (#66), Grok 4: 51.8 (#103)

BenchmarkGLM-4.6Grok 4
LMArena Non-English14261403
LMArena Chinese14991427
LMArena French14591418
LMArena German14471429
LMArena Japanese13931394
LMArena Korean14001377
LMArena Russian14191410
LMArena Spanish14361420

Instruction Following Grok 4 leads

GLM-4.6: 74.3 (#98), Grok 4: 79.2 (#5)

BenchmarkGLM-4.6Grok 4
LMArena Instruction Following14101387
IFEval—94.9%

Long Context Grok 4 leads

GLM-4.6: 43.4 (#94), Grok 4: 63.1 (#4)

BenchmarkGLM-4.6Grok 4
LMArena Longer Query14221409
Fiction.LiveBench—94.4%

Writing & Preference GLM-4.6 leads

GLM-4.6: 61.1 (#90), Grok 4: 58.5 (#116)

BenchmarkGLM-4.6Grok 4
LMArena Text14401411
LMArena Creative Writing14111397
LMArena Multi-Turn14271416
Short-Story Creative Writing—76.9%
EQ-Bench Creative Writing1411—
WildBench—79.7%

Frequently asked questions

Is GLM-4.6 better than Grok 4?

Grok 4 is the stronger model overall, scoring 48.1 to 41.4 on the Noometry Index.

Is GLM-4.6 or Grok 4 better for coding?

Grok 4 scores higher on coding benchmarks: 50.3 versus 40.1 in the Noometry coding category.

How many benchmarks do GLM-4.6 and Grok 4 share?

22 benchmarks have published results for both models. GLM-4.6 has 29 scored results on Noometry and Grok 4 has 48.

Related comparisons

Go deeper