Noometry

Model comparison

GLM-4.7 vs Grok 3

GLM-4.7 is the stronger model overall, scoring 41.7 to 39.6 on the Noometry Index.

Last verified . 25 shared benchmarks.

GLM-4.7 Z.ai (Zhipu)

41.7

Rank #117 Confirmed

Grok 3 xAI

39.6

Rank #150 Confirmed

Summary

  • They share 25 benchmarks with published results for both. GLM-4.7 scores higher in 7 categories and Grok 3 in 2 categories; 6 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where GLM-4.7 leads 23.7 to 13.8.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 83.3% for GLM-4.7 and 55.6% for Grok 3.
  • GLM-4.7 has downloadable open weights; the other is API-only.

Side by side

GLM-4.7Grok 3
ProviderZ.ai (Zhipu)xAI
Noometry Index41.739.6
Released2025-12-222025-04-09
WeightsOpenProprietary
Context window205K—
Max output131K—
Input $ / M tokens$0.60—
Output $ / M tokens$2.20—
Results tracked3640

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

Category by category

Coding GLM-4.7 leads

GLM-4.7: 43.6 (#74), Grok 3: 41.5 (#113)

BenchmarkGLM-4.7Grok 3
LMArena Coding14541432
Aider Polyglot—53.3%
LMArena WebDev1435—
SciCode45.1%—
WeirdML—37.2%
ALE-Bench399.48—

Agentic & Tool Use Grok 3 leads

GLM-4.7: 26.4 (#96), Grok 3: 30.2 (#69)

BenchmarkGLM-4.7Grok 3
Terminal-Bench33.4%—
BALROG—29.5%
Vending-Bench 22,377—

Reasoning GLM-4.7 leads

GLM-4.7: 23.7 (#161), Grok 3: 13.8 (#322)

BenchmarkGLM-4.7Grok 3
SimpleBench47.7%36.1%
LMArena Hard Prompts14431433
Epoch Capabilities Index143.53138.34
ARC-AGI-2—0%
Kagi LLM Benchmark—61.3%
ARC-AGI-1—5.5%
CritPt1.7%—
Chess Puzzles6%—

Math GLM-4.7 leads

GLM-4.7: 37.7 (#92), Grok 3: 36.2 (#122)

BenchmarkGLM-4.7Grok 3
OTIS Mock AIME 2024-202583.3%55.6%
LMArena Math14231390
FrontierMath (Feb 2025 set)2.4%3.8%
FrontierMath Tier 4 (v1)0%0%
ProofBench6%—
Omni-MATH—46.4%
MATH Level 5—88.7%

Knowledge Too close to call

GLM-4.7: 47.0 (#74), Grok 3: 46.0 (#76)

BenchmarkGLM-4.7Grok 3
GPQA Diamond83.3%75.8%
Vectara Hallucination Rate11.7%5.8%
LMArena Expert14241420
SimpleQA Verified32.2%—
MMLU-Pro—78.8%
Confabulations—14.2%
GPQA (HELM)—65%

Multilingual Too close to call

GLM-4.7: 53.0 (#75), Grok 3: 52.5 (#81)

BenchmarkGLM-4.7Grok 3
LMArena Non-English14171411
LMArena Chinese14951448
LMArena French14321460
LMArena German14261431
LMArena Japanese14391389
LMArena Korean14011374
LMArena Russian14231416
LMArena Spanish14331417

Instruction Following Too close to call

GLM-4.7: 74.6 (#90), Grok 3: 75.2 (#69)

BenchmarkGLM-4.7Grok 3
LMArena Instruction Following14111409
IFEval—88.4%

Long Context GLM-4.7 leads

GLM-4.7: 42.8 (#111), Grok 3: 38.7 (#187)

BenchmarkGLM-4.7Grok 3
LMArena Longer Query14321439
Fiction.LiveBench—58.3%
CL-bench15.9%—
CL-bench Life10.9%—

Writing & Preference GLM-4.7 leads

GLM-4.7: 61.1 (#89), Grok 3: 56.0 (#136)

BenchmarkGLM-4.7Grok 3
LMArena Text14361426
LMArena Creative Writing14011414
EQ-Bench Creative Writing14131186
LMArena Multi-Turn14461424
Short-Story Creative Writing—76.4%
WildBench—84.9%

Frequently asked questions

Is GLM-4.7 better than Grok 3?

GLM-4.7 is the stronger model overall, scoring 41.7 to 39.6 on the Noometry Index.

Is GLM-4.7 or Grok 3 better for coding?

GLM-4.7 scores higher on coding benchmarks: 43.6 versus 41.5 in the Noometry coding category.

How many benchmarks do GLM-4.7 and Grok 3 share?

25 benchmarks have published results for both models. GLM-4.7 has 36 scored results on Noometry and Grok 3 has 40.

Related comparisons

Go deeper