Noometry

Model comparison

GLM-4.7 vs GPT-4 Turbo

GLM-4.7 is the stronger model overall, scoring 41.7 to 30.3 on the Noometry Index.

Last verified . 22 shared benchmarks.

GLM-4.7 Z.ai (Zhipu)

41.7

Rank #117 Confirmed

GPT-4 Turbo OpenAI

30.3

Rank #281 Confirmed

Summary

  • They share 22 benchmarks with published results for both. GLM-4.7 scores higher in 8 categories and GPT-4 Turbo in 0 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in math, where GLM-4.7 leads 37.7 to 8.6.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 83.3% for GLM-4.7 and 6.7% for GPT-4 Turbo.
  • GLM-4.7 is cheaper at $0.60 / $2.20 per million input/output tokens, against $10 / $30 for GPT-4 Turbo.
  • GLM-4.7 accepts more context: 205K tokens versus 128K.
  • GLM-4.7 has downloadable open weights; the other is API-only.

Side by side

GLM-4.7GPT-4 Turbo
ProviderZ.ai (Zhipu)OpenAI
Noometry Index41.730.3
Released2025-12-222023-11-06
WeightsOpenProprietary
Context window205K128K
Max output131K4K
Input $ / M tokens$0.60$10
Output $ / M tokens$2.20$30
Results tracked3636

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 Turbo: 33.4 (#247)

BenchmarkGLM-4.7GPT-4 Turbo
LMArena Coding14541268
LMArena WebDev1435—
SciCode45.1%—
WeirdML—18%
BigCodeBench Instruct—48.2%
BigCodeBench Complete—58.2%
ALE-Bench399.48—
HumanEval+—86.6%
MBPP+—73.3%

Agentic & Tool Use Not comparable

GLM-4.7: 26.4 (#96), GPT-4 Turbo: —

BenchmarkGLM-4.7GPT-4 Turbo
Terminal-Bench33.4%—
METR Time Horizons—36.7%
Vending-Bench 22,377—

Reasoning GLM-4.7 leads

GLM-4.7: 23.7 (#161), GPT-4 Turbo: 14.9 (#311)

BenchmarkGLM-4.7GPT-4 Turbo
SimpleBench47.7%25.1%
Chess Puzzles6%6%
LMArena Hard Prompts14431251
Epoch Capabilities Index143.53127.25
CritPt1.7%—
DTBench—61.6%
LMCA—9.8%
ForecastBench—59.4

Math GLM-4.7 leads

GLM-4.7: 37.7 (#92), GPT-4 Turbo: 8.6 (#316)

BenchmarkGLM-4.7GPT-4 Turbo
OTIS Mock AIME 2024-202583.3%6.7%
LMArena Math14231272
FrontierMath (Tiers 1-3)—0.7%
ProofBench6%—
MATH Level 5—46.7%
FrontierMath (Feb 2025 set)2.4%—
FrontierMath Tier 4 (v1)0%—

Knowledge GLM-4.7 leads

GLM-4.7: 47.0 (#74), GPT-4 Turbo: 24.3 (#263)

BenchmarkGLM-4.7GPT-4 Turbo
GPQA Diamond83.3%46.6%
LMArena Expert14241223
SimpleQA Verified32.2%—
Confabulations—28.4%
Vectara Hallucination Rate11.7%—
MMLU—81.3%

Multimodal Not comparable

GLM-4.7: —, GPT-4 Turbo: 30.0 (#104)

BenchmarkGLM-4.7GPT-4 Turbo
LMArena Vision—1090

Multilingual GLM-4.7 leads

GLM-4.7: 53.0 (#75), GPT-4 Turbo: 40.7 (#211)

BenchmarkGLM-4.7GPT-4 Turbo
LMArena Non-English14171245
LMArena Chinese14951242
LMArena French14321275
LMArena German14261259
LMArena Japanese14391194
LMArena Korean14011187
LMArena Russian14231259
LMArena Spanish14331260

Instruction Following GLM-4.7 leads

GLM-4.7: 74.6 (#90), GPT-4 Turbo: 66.0 (#211)

BenchmarkGLM-4.7GPT-4 Turbo
LMArena Instruction Following14111250

Long Context GLM-4.7 leads

GLM-4.7: 42.8 (#111), GPT-4 Turbo: 38.0 (#200)

BenchmarkGLM-4.7GPT-4 Turbo
LMArena Longer Query14321254
CL-bench15.9%—
CL-bench Life10.9%—

Writing & Preference GLM-4.7 leads

GLM-4.7: 61.1 (#89), GPT-4 Turbo: 47.9 (#201)

BenchmarkGLM-4.7GPT-4 Turbo
LMArena Text14361272
LMArena Creative Writing14011269
LMArena Multi-Turn14461267
EQ-Bench Creative Writing1413—

Frequently asked questions

Is GLM-4.7 better than GPT-4 Turbo?

GLM-4.7 is the stronger model overall, scoring 41.7 to 30.3 on the Noometry Index.

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

GLM-4.7 is cheaper. It lists at $0.60 per million input tokens and $2.20 per million output tokens; GPT-4 Turbo lists at $10 and $30.

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

GLM-4.7 scores higher on coding benchmarks: 43.6 versus 33.4 in the Noometry coding category.

Which has the bigger context window?

GLM-4.7 does, with 205K tokens against 128K.

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

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

Related comparisons

Go deeper