Noometry

Model comparison

GLM-4.7 vs Grok-2 (Dec 2024)

GLM-4.7 is the stronger model overall, scoring 42.0 to 33.7 on the Noometry Index.

Last verified . 22 shared benchmarks.

GLM-4.7 Z.ai (Zhipu)

42.0

Rank #124 Confirmed

Grok-2 (Dec 2024) xAI

33.7

Rank #239 Confirmed

Summary

  • They share 22 benchmarks with published results for both. GLM-4.7 scores higher in 8 categories and Grok-2 (Dec 2024) in 0 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in math, where GLM-4.7 leads 38.6 to 20.8.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 83.3% for GLM-4.7 and 11.5% for Grok-2 (Dec 2024).
  • GLM-4.7 has downloadable open weights; the other is API-only.

Side by side

GLM-4.7Grok-2 (Dec 2024)
ProviderZ.ai (Zhipu)xAI
Noometry Index42.033.7
Released2025-12-222024-08-13
WeightsOpenProprietary
Context window205K—
Max output131K—
Input $ / M tokens$0.60—
Output $ / M tokens$2.20—
Results tracked3634

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

Category by category

Coding GLM-4.7 leads

GLM-4.7: 44.0 (#79), Grok-2 (Dec 2024): 33.3 (#258)

BenchmarkGLM-4.7Grok-2 (Dec 2024)
LMArena Coding14541287
LMArena WebDev1435—
SciCode45.1%—
WeirdML—22.2%
LiveBench Coding—46.4%
ALE-Bench399.48—

Agentic & Tool Use Not comparable

GLM-4.7: 26.5 (#103), Grok-2 (Dec 2024): —

BenchmarkGLM-4.7Grok-2 (Dec 2024)
Terminal-Bench33.4%—
Vending-Bench 22,377—

Reasoning GLM-4.7 leads

GLM-4.7: 24.3 (#164), Grok-2 (Dec 2024): 16.9 (#299)

BenchmarkGLM-4.7Grok-2 (Dec 2024)
SimpleBench47.7%22.7%
LMArena Hard Prompts14431272
Epoch Capabilities Index143.51130.48
CritPt1.7%—
Chess Puzzles6%—
LiveBench Reasoning—54.8%
DTBench—65.2%
LiveBench Data Analysis—54.5%
LiveBench—54.3%

Math GLM-4.7 leads

GLM-4.7: 38.6 (#135), Grok-2 (Dec 2024): 20.8 (#284)

BenchmarkGLM-4.7Grok-2 (Dec 2024)
OTIS Mock AIME 2024-202583.3%11.5%
LMArena Math14231283
FrontierMath (Feb 2025 set)2.4%0.7%
ProofBench6%—
LiveBench Math—54.9%
MATH Level 5—63.5%
FrontierMath Tier 4 (v1)0%—

Knowledge GLM-4.7 leads

GLM-4.7: 47.0 (#80), Grok-2 (Dec 2024): 29.8 (#233)

BenchmarkGLM-4.7Grok-2 (Dec 2024)
GPQA Diamond83.3%53.8%
LMArena Expert14241254
SimpleQA Verified32.2%—
Confabulations—20.1%
Vectara Hallucination Rate11.7%—

Multilingual GLM-4.7 leads

GLM-4.7: 52.8 (#79), Grok-2 (Dec 2024): 43.1 (#188)

BenchmarkGLM-4.7Grok-2 (Dec 2024)
LMArena Non-English14171282
LMArena Chinese14951289
LMArena French14321318
LMArena German14241287
LMArena Japanese14391244
LMArena Korean13991237
LMArena Russian14231286
LMArena Spanish14341281

Instruction Following GLM-4.7 leads

GLM-4.7: 74.4 (#95), Grok-2 (Dec 2024): 66.9 (#202)

BenchmarkGLM-4.7Grok-2 (Dec 2024)
LMArena Instruction Following14111270
LiveBench Instruction Following—69.6%

Long Context GLM-4.7 leads

GLM-4.7: 42.8 (#116), Grok-2 (Dec 2024): 38.8 (#190)

BenchmarkGLM-4.7Grok-2 (Dec 2024)
LMArena Longer Query14321276
CL-bench15.9%—
CL-bench Life10.9%—

Writing & Preference GLM-4.7 leads

GLM-4.7: 60.9 (#93), Grok-2 (Dec 2024): 48.6 (#198)

BenchmarkGLM-4.7Grok-2 (Dec 2024)
LMArena Text14351305
LMArena Creative Writing14011284
LMArena Multi-Turn14461290
Short-Story Creative Writing—63.6%
EQ-Bench Creative Writing1413—
LiveBench Language—45.6%

Frequently asked questions

Is GLM-4.7 better than Grok-2 (Dec 2024)?

GLM-4.7 is the stronger model overall, scoring 42.0 to 33.7 on the Noometry Index.

Is GLM-4.7 or Grok-2 (Dec 2024) better for coding?

GLM-4.7 scores higher on coding benchmarks: 44.0 versus 33.3 in the Noometry coding category.

How many benchmarks do GLM-4.7 and Grok-2 (Dec 2024) share?

22 benchmarks have published results for both models. GLM-4.7 has 36 scored results on Noometry and Grok-2 (Dec 2024) has 34.

Related comparisons

Go deeper