Noometry

Model comparison

GLM-5.1 vs Grok 4

GLM-5.1 and Grok 4 score almost the same on the Noometry Index (47.8 vs 48.1), so choose on price, context window or the category you care about most.

Last verified . 25 shared benchmarks.

GLM-5.1 Z.ai (Zhipu)

47.8

Rank #59 Confirmed

Grok 4 xAI

48.1

Rank #56 Confirmed

Summary

  • They share 25 benchmarks with published results for both. GLM-5.1 scores higher in 5 categories and Grok 4 in 4 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in long context, where Grok 4 leads 63.1 to 44.9.
  • The biggest single-benchmark swing is WeirdML: 57.1% for GLM-5.1 and 45.7% for Grok 4.
  • GLM-5.1 has downloadable open weights; the other is API-only.

Side by side

GLM-5.1Grok 4
ProviderZ.ai (Zhipu)xAI
Noometry Index47.848.1
Released2026-04-072025-07-09
WeightsOpenProprietary
Context window200K—
Max output131K—
Input $ / M tokens$1.40—
Output $ / M tokens$4.40—
Results tracked4148

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

Category by category

Coding Grok 4 leads

GLM-5.1: 48.7 (#55), Grok 4: 50.3 (#46)

BenchmarkGLM-5.1Grok 4
WeirdML57.1%45.7%
LMArena Coding14851408
SWE-bench Verified74.2%—
Aider Polyglot—79.6%
LMArena WebDev1508—
SciCode43.8%—
ALE-Bench887.1—

Agentic & Tool Use Grok 4 leads

GLM-5.1: 24.9 (#113), Grok 4: 32.3 (#68)

BenchmarkGLM-5.1Grok 4
Terminal-Bench—27.2%
APEX-Agents40.9%—
Berkeley Function Calling Leaderboard—63%
GDPval—21.1%
Cybench—43%
DeepResearch Bench—47.3%
BALROG—43.6%
ExploitBench18.1%—
GBAEval0%—
LMArena Search—1142
METR Time Horizons—66.6%
Vending-Bench 25,634—

Reasoning GLM-5.1 leads

GLM-5.1: 39.1 (#60), Grok 4: 36.7 (#65)

BenchmarkGLM-5.1Grok 4
SimpleBench55.1%60.5%
Chess Puzzles19%28%
LMArena Hard Prompts14721409
Epoch Capabilities Index149.84146.44
ARC-AGI-2—16%
Kagi LLM Benchmark—73.6%
NYT Connections (extended)77.7%—
ARC-AGI-1—66.7%
CritPt4.6%—
Thematic Generalization69.8%—
ForecastBench—60.9

Math GLM-5.1 leads

GLM-5.1: 49.7 (#60), Grok 4: 48.4 (#64)

BenchmarkGLM-5.1Grok 4
OTIS Mock AIME 2024-202593.3%84%
LMArena Math14731422
FrontierMath (Feb 2025 set)33.4%19.7%
FrontierMath Tier 4 (v1)12.5%2.1%
FrontierMath (Tiers 1-3)36.8%—
MathArena Final-Answer Competitions67.1%—
ProofBench22.2%—
Omni-MATH—60.3%

Knowledge GLM-5.1 leads

GLM-5.1: 54.9 (#50), Grok 4: 53.8 (#55)

BenchmarkGLM-5.1Grok 4
GPQA Diamond89.9%87%
LMArena Expert14761415
SimpleQA Verified34%—
MMLU-Pro—85.1%
Confabulations—12.4%
GPQA (HELM)—72.7%

Multimodal Not comparable

GLM-5.1: —, Grok 4: 33.7 (#94)

BenchmarkGLM-5.1Grok 4
LMArena Vision—1210
GeoBench—45%

Multilingual GLM-5.1 leads

GLM-5.1: 55.0 (#36), Grok 4: 51.8 (#103)

BenchmarkGLM-5.1Grok 4
LMArena Non-English14471403
LMArena Chinese15151427
LMArena French14741418
LMArena German14651429
LMArena Japanese14341394
LMArena Korean14181377
LMArena Russian14541410
LMArena Spanish14691420

Instruction Following Grok 4 leads

GLM-5.1: 76.3 (#42), Grok 4: 79.2 (#5)

BenchmarkGLM-5.1Grok 4
LMArena Instruction Following14511387
IFEval—94.9%

Long Context Grok 4 leads

GLM-5.1: 44.9 (#53), Grok 4: 63.1 (#4)

BenchmarkGLM-5.1Grok 4
LMArena Longer Query14661409
Fiction.LiveBench—94.4%

Writing & Preference GLM-5.1 leads

GLM-5.1: 66.9 (#31), Grok 4: 58.5 (#116)

BenchmarkGLM-5.1Grok 4
LMArena Text14611411
LMArena Creative Writing14531397
LMArena Multi-Turn14721416
Short-Story Creative Writing—76.9%
EQ-Bench Creative Writing1592—
WildBench—79.7%

Frequently asked questions

Is GLM-5.1 better than Grok 4?

GLM-5.1 and Grok 4 score almost the same on the Noometry Index (47.8 vs 48.1), so choose on price, context window or the category you care about most.

Is GLM-5.1 or Grok 4 better for coding?

Grok 4 scores higher on coding benchmarks: 50.3 versus 48.7 in the Noometry coding category.

How many benchmarks do GLM-5.1 and Grok 4 share?

25 benchmarks have published results for both models. GLM-5.1 has 41 scored results on Noometry and Grok 4 has 48.

Related comparisons

Go deeper