Noometry

Model comparison

GLM-5 vs Grok 4

Grok 4 is the stronger model overall, scoring 48.1 to 46.1 on the Noometry Index.

Last verified . 30 shared benchmarks.

GLM-5 Z.ai (Zhipu)

46.1

Rank #66 Confirmed

Grok 4 xAI

48.1

Rank #56 Confirmed

Summary

  • They share 30 benchmarks with published results for both. GLM-5 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 44.7.
  • The biggest single-benchmark swing is Terminal-Bench: 52.4% for GLM-5 and 27.2% for Grok 4.
  • GLM-5 has downloadable open weights; the other is API-only.

Side by side

GLM-5Grok 4
ProviderZ.ai (Zhipu)xAI
Noometry Index46.148.1
Released2026-02-112025-07-09
WeightsOpenProprietary
Context window205K—
Max output131K—
Input $ / M tokens$1—
Output $ / M tokens$3.20—
Results tracked4548

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

Category by category

Coding Grok 4 leads

GLM-5: 49.0 (#52), Grok 4: 50.3 (#46)

BenchmarkGLM-5Grok 4
WeirdML48.2%45.7%
LMArena Coding14611408
SWE-bench Verified72.1%—
SWE-bench Verified (bash only)72.8%—
Aider Polyglot—79.6%
LMArena WebDev1434—
SWE-bench Multilingual69.7%—
ALE-Bench765.62—

Agentic & Tool Use Grok 4 leads

GLM-5: 31.1 (#71), Grok 4: 32.3 (#68)

BenchmarkGLM-5Grok 4
Terminal-Bench52.4%27.2%
Berkeley Function Calling Leaderboard—63%
GDPval—21.1%
τ²-bench Airline82.5%—
τ²-bench Banking9.8%—
τ²-bench Retail73.7%—
τ²-bench Telecom86.8%—
Cybench—43%
DeepResearch Bench—47.3%
BALROG—43.6%
LMArena Search—1142
METR Time Horizons—66.6%
Vending-Bench 24,432—

Reasoning Grok 4 leads

GLM-5: 27.6 (#116), Grok 4: 36.7 (#65)

BenchmarkGLM-5Grok 4
ARC-AGI-24.9%16%
SimpleBench53.2%60.5%
Kagi LLM Benchmark75%73.6%
ARC-AGI-144.7%66.7%
Chess Puzzles10%28%
LMArena Hard Prompts14521409
Epoch Capabilities Index145.83146.44
ForecastBench6160.9
NYT Connections (extended)74.8%—

Math Grok 4 leads

GLM-5: 46.4 (#71), Grok 4: 48.4 (#64)

BenchmarkGLM-5Grok 4
OTIS Mock AIME 2024-202580%84%
LMArena Math14401422
FrontierMath (Feb 2025 set)16.4%19.7%
FrontierMath Tier 4 (v1)2.1%2.1%
MathArena Final-Answer Competitions65.7%—
Omni-MATH—60.3%

Knowledge Grok 4 leads

GLM-5: 52.3 (#64), Grok 4: 53.8 (#55)

BenchmarkGLM-5Grok 4
GPQA Diamond87.8%87%
LMArena Expert14541415
MMLU-Pro—85.1%
Confabulations—12.4%
Vectara Hallucination Rate10.1%—
GPQA (HELM)—72.7%

Multimodal Not comparable

GLM-5: —, Grok 4: 33.7 (#94)

BenchmarkGLM-5Grok 4
LMArena Vision—1210
GeoBench—45%

Multilingual GLM-5 leads

GLM-5: 53.7 (#58), Grok 4: 51.8 (#103)

BenchmarkGLM-5Grok 4
LMArena Non-English14301403
LMArena Chinese15111427
LMArena French14551418
LMArena German14451429
LMArena Japanese14161394
LMArena Korean14231377
LMArena Russian14361410
LMArena Spanish14541420

Instruction Following Grok 4 leads

GLM-5: 75.2 (#67), Grok 4: 79.2 (#5)

BenchmarkGLM-5Grok 4
LMArena Instruction Following14281387
IFEval—94.9%

Long Context Grok 4 leads

GLM-5: 44.7 (#60), Grok 4: 63.1 (#4)

BenchmarkGLM-5Grok 4
LMArena Longer Query14461409
Fiction.LiveBench—94.4%
CL-bench18.7%—

Writing & Preference GLM-5 leads

GLM-5: 66.0 (#38), Grok 4: 58.5 (#116)

BenchmarkGLM-5Grok 4
LMArena Text14461411
LMArena Creative Writing14391397
LMArena Multi-Turn14561416
Short-Story Creative Writing—76.9%
EQ-Bench Creative Writing1601—
WildBench—79.7%

Frequently asked questions

Is GLM-5 better than Grok 4?

Grok 4 is the stronger model overall, scoring 48.1 to 46.1 on the Noometry Index.

Is GLM-5 or Grok 4 better for coding?

Grok 4 scores higher on coding benchmarks: 50.3 versus 49.0 in the Noometry coding category.

How many benchmarks do GLM-5 and Grok 4 share?

30 benchmarks have published results for both models. GLM-5 has 45 scored results on Noometry and Grok 4 has 48.

Related comparisons

Go deeper