Noometry

Model comparison

GLM-4.7 vs GPT-4

GLM-4.7 is the stronger model overall, scoring 41.7 to 28.9 on the Noometry Index.

Last verified . 22 shared benchmarks.

GLM-4.7 Z.ai (Zhipu)

41.7

Rank #117 Confirmed

GPT-4 OpenAI

28.9

Rank #308 Confirmed

Summary

  • They share 22 benchmarks with published results for both. GLM-4.7 scores higher in 8 categories and GPT-4 in 0 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where GLM-4.7 leads 47.0 to 18.4.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 83.3% for GLM-4.7 and 1.1% for GPT-4.
  • GLM-4.7 is cheaper at $0.60 / $2.20 per million input/output tokens, against $30 / $60 for GPT-4.
  • GLM-4.7 accepts more context: 205K tokens versus 8K.
  • GLM-4.7 has downloadable open weights; the other is API-only.

Side by side

GLM-4.7GPT-4
ProviderZ.ai (Zhipu)OpenAI
Noometry Index41.728.9
Released2025-12-222023-03-14
WeightsOpenProprietary
Context window205K8K
Max output131K8K
Input $ / M tokens$0.60$30
Output $ / M tokens$2.20$60
Results tracked3638

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), GPT-4: 31.2 (#277)

BenchmarkGLM-4.7GPT-4
LMArena Coding14541254
LMArena WebDev1435—
SciCode45.1%—
WeirdML—12.4%
BigCodeBench Instruct—46%
BigCodeBench Complete—57.2%
ALE-Bench399.48—
HumanEval+—79.3%

Agentic & Tool Use Not comparable

GLM-4.7: 26.4 (#96), GPT-4: —

BenchmarkGLM-4.7GPT-4
Terminal-Bench33.4%—
METR Time Horizons—36.1%
Vending-Bench 22,377—

Reasoning GLM-4.7 leads

GLM-4.7: 23.7 (#161), GPT-4: 17.3 (#285)

BenchmarkGLM-4.7GPT-4
Chess Puzzles6%4%
LMArena Hard Prompts14431241
Epoch Capabilities Index143.53125.88
SimpleBench47.7%—
CritPt1.7%—
Mystery Game Puzzles—12%
DTBench—62.7%
LMCA—17.1%
BIG-Bench Hard—75.1%
ForecastBench—57.8
HellaSwag—95.3%
WinoGrande—87.5%

Math GLM-4.7 leads

GLM-4.7: 37.7 (#92), GPT-4: 10.1 (#304)

BenchmarkGLM-4.7GPT-4
OTIS Mock AIME 2024-202583.3%1.1%
LMArena Math14231269
ProofBench6%—
MATH Level 5—23%
FrontierMath (Feb 2025 set)2.4%—
FrontierMath Tier 4 (v1)0%—
GSM8K—92%

Knowledge GLM-4.7 leads

GLM-4.7: 47.0 (#74), GPT-4: 18.4 (#277)

BenchmarkGLM-4.7GPT-4
GPQA Diamond83.3%35.7%
LMArena Expert14241211
SimpleQA Verified32.2%—
Vectara Hallucination Rate11.7%—
MMLU—86.4%
TriviaQA—84.8%

Multilingual GLM-4.7 leads

GLM-4.7: 53.0 (#75), GPT-4: 40.8 (#210)

BenchmarkGLM-4.7GPT-4
LMArena Non-English14171246
LMArena Chinese14951242
LMArena French14321282
LMArena German14261251
LMArena Japanese14391209
LMArena Korean14011184
LMArena Russian14231251
LMArena Spanish14331261

Instruction Following GLM-4.7 leads

GLM-4.7: 74.6 (#90), GPT-4: 65.5 (#217)

BenchmarkGLM-4.7GPT-4
LMArena Instruction Following14111241

Long Context GLM-4.7 leads

GLM-4.7: 42.8 (#111), GPT-4: 37.7 (#207)

BenchmarkGLM-4.7GPT-4
LMArena Longer Query14321244
CL-bench15.9%—
CL-bench Life10.9%—

Writing & Preference GLM-4.7 leads

GLM-4.7: 61.1 (#89), GPT-4: 35.0 (#263)

BenchmarkGLM-4.7GPT-4
LMArena Text14361263
LMArena Creative Writing14011244
EQ-Bench Creative Writing1413752
LMArena Multi-Turn14461257

Frequently asked questions

Is GLM-4.7 better than GPT-4?

GLM-4.7 is the stronger model overall, scoring 41.7 to 28.9 on the Noometry Index.

Which is cheaper, GLM-4.7 or GPT-4?

GLM-4.7 is cheaper. It lists at $0.60 per million input tokens and $2.20 per million output tokens; GPT-4 lists at $30 and $60.

Is GLM-4.7 or GPT-4 better for coding?

GLM-4.7 scores higher on coding benchmarks: 43.6 versus 31.2 in the Noometry coding category.

Which has the bigger context window?

GLM-4.7 does, with 205K tokens against 8K.

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

22 benchmarks have published results for both models. GLM-4.7 has 36 scored results on Noometry and GPT-4 has 38.

Related comparisons

Go deeper