Noometry

Model comparison

GLM-4.7 vs Grok 4

Grok 4 is the stronger model overall, scoring 48.1 to 42.0 on the Noometry Index.

Last verified . 25 shared benchmarks.

GLM-4.7 Z.ai (Zhipu)

42.0

Rank #124 Confirmed

Grok 4 xAI

48.1

Rank #56 Confirmed

Summary

  • They share 25 benchmarks with published results for both. GLM-4.7 scores higher in 2 categories and Grok 4 in 7 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in long context, where Grok 4 leads 63.1 to 42.8.
  • The biggest single-benchmark swing is Chess Puzzles: 6% for GLM-4.7 and 28% for Grok 4.
  • GLM-4.7 has downloadable open weights; the other is API-only.

Side by side

GLM-4.7Grok 4
ProviderZ.ai (Zhipu)xAI
Noometry Index42.048.1
Released2025-12-222025-07-09
WeightsOpenProprietary
Context window205K—
Max output131K—
Input $ / M tokens$0.60—
Output $ / M tokens$2.20—
Results tracked3648

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

Category by category

Coding Grok 4 leads

GLM-4.7: 44.0 (#79), Grok 4: 50.3 (#46)

BenchmarkGLM-4.7Grok 4
LMArena Coding14541408
Aider Polyglot—79.6%
LMArena WebDev1435—
SciCode45.1%—
WeirdML—45.7%
ALE-Bench399.48—

Agentic & Tool Use Grok 4 leads

GLM-4.7: 26.5 (#103), Grok 4: 32.3 (#68)

BenchmarkGLM-4.7Grok 4
Terminal-Bench33.4%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%
Vending-Bench 22,377—

Reasoning Grok 4 leads

GLM-4.7: 24.3 (#164), Grok 4: 36.7 (#65)

BenchmarkGLM-4.7Grok 4
SimpleBench47.7%60.5%
Chess Puzzles6%28%
LMArena Hard Prompts14431409
Epoch Capabilities Index143.51146.44
ARC-AGI-2—16%
Kagi LLM Benchmark—73.6%
ARC-AGI-1—66.7%
CritPt1.7%—
ForecastBench—60.9

Math Grok 4 leads

GLM-4.7: 38.6 (#135), Grok 4: 48.4 (#64)

BenchmarkGLM-4.7Grok 4
OTIS Mock AIME 2024-202583.3%84%
LMArena Math14231422
FrontierMath (Feb 2025 set)2.4%19.7%
FrontierMath Tier 4 (v1)0%2.1%
ProofBench6%—
Omni-MATH—60.3%

Knowledge Grok 4 leads

GLM-4.7: 47.0 (#80), Grok 4: 53.8 (#55)

BenchmarkGLM-4.7Grok 4
GPQA Diamond83.3%87%
LMArena Expert14241415
SimpleQA Verified32.2%—
MMLU-Pro—85.1%
Confabulations—12.4%
Vectara Hallucination Rate11.7%—
GPQA (HELM)—72.7%

Multimodal Not comparable

GLM-4.7: —, Grok 4: 33.7 (#94)

BenchmarkGLM-4.7Grok 4
LMArena Vision—1210
GeoBench—45%

Multilingual GLM-4.7 leads

GLM-4.7: 52.8 (#79), Grok 4: 51.8 (#103)

BenchmarkGLM-4.7Grok 4
LMArena Non-English14171403
LMArena Chinese14951427
LMArena French14321418
LMArena German14241429
LMArena Japanese14391394
LMArena Korean13991377
LMArena Russian14231410
LMArena Spanish14341420

Instruction Following Grok 4 leads

GLM-4.7: 74.4 (#95), Grok 4: 79.2 (#5)

BenchmarkGLM-4.7Grok 4
LMArena Instruction Following14111387
IFEval—94.9%

Long Context Grok 4 leads

GLM-4.7: 42.8 (#116), Grok 4: 63.1 (#4)

BenchmarkGLM-4.7Grok 4
LMArena Longer Query14321409
Fiction.LiveBench—94.4%
CL-bench15.9%—
CL-bench Life10.9%—

Writing & Preference GLM-4.7 leads

GLM-4.7: 60.9 (#93), Grok 4: 58.5 (#116)

BenchmarkGLM-4.7Grok 4
LMArena Text14351411
LMArena Creative Writing14011397
LMArena Multi-Turn14461416
Short-Story Creative Writing—76.9%
EQ-Bench Creative Writing1413—
WildBench—79.7%

Frequently asked questions

Is GLM-4.7 better than Grok 4?

Grok 4 is the stronger model overall, scoring 48.1 to 42.0 on the Noometry Index.

Is GLM-4.7 or Grok 4 better for coding?

Grok 4 scores higher on coding benchmarks: 50.3 versus 44.0 in the Noometry coding category.

How many benchmarks do GLM-4.7 and Grok 4 share?

25 benchmarks have published results for both models. GLM-4.7 has 36 scored results on Noometry and Grok 4 has 48.

Related comparisons

Go deeper