Noometry

Model comparison

GLM-4.7-Flash vs GPT-4

GLM-4.7-Flash is the stronger model overall, scoring 38.4 to 28.9 on the Noometry Index.

Last verified . 20 shared benchmarks.

GLM-4.7-Flash Z.ai (Zhipu)

38.4

Rank #175 Confirmed

GPT-4 OpenAI

28.9

Rank #308 Confirmed

Summary

  • They share 20 benchmarks with published results for both. GLM-4.7-Flash scores higher in 8 categories and GPT-4 in 0 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in math, where GLM-4.7-Flash leads 34.4 to 10.1.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 58.3% for GLM-4.7-Flash and 1.1% for GPT-4.
  • GLM-4.7-Flash is cheaper at $0.06 / $0.40 per million input/output tokens, against $30 / $60 for GPT-4.
  • GLM-4.7-Flash accepts more context: 200K tokens versus 8K.
  • GLM-4.7-Flash has downloadable open weights; the other is API-only.

Side by side

GLM-4.7-FlashGPT-4
ProviderZ.ai (Zhipu)OpenAI
Noometry Index38.428.9
Released2026-01-192023-03-14
WeightsOpenProprietary
Context window200K8K
Max output131K8K
Input $ / M tokens$0.06$30
Output $ / M tokens$0.40$60
Results tracked2138

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

Category by category

Coding GLM-4.7-Flash leads

GLM-4.7-Flash: 40.0 (#133), GPT-4: 31.2 (#277)

BenchmarkGLM-4.7-FlashGPT-4
LMArena Coding13831254
WeirdML—12.4%
BigCodeBench Instruct—46%
BigCodeBench Complete—57.2%
HumanEval+—79.3%

Agentic & Tool Use Not comparable

GLM-4.7-Flash: —, GPT-4: —

BenchmarkGLM-4.7-FlashGPT-4
METR Time Horizons—36.1%

Reasoning GLM-4.7-Flash leads

GLM-4.7-Flash: 20.2 (#224), GPT-4: 17.3 (#285)

BenchmarkGLM-4.7-FlashGPT-4
Chess Puzzles0%4%
LMArena Hard Prompts13561241
Mystery Game Puzzles—12%
DTBench—62.7%
LMCA—17.1%
BIG-Bench Hard—75.1%
Epoch Capabilities Index—125.88
ForecastBench—57.8
HellaSwag—95.3%
WinoGrande—87.5%

Math GLM-4.7-Flash leads

GLM-4.7-Flash: 34.4 (#159), GPT-4: 10.1 (#304)

BenchmarkGLM-4.7-FlashGPT-4
OTIS Mock AIME 2024-202558.3%1.1%
LMArena Math13541269
MATH Level 5—23%
GSM8K—92%

Knowledge GLM-4.7-Flash leads

GLM-4.7-Flash: 35.4 (#177), GPT-4: 18.4 (#277)

BenchmarkGLM-4.7-FlashGPT-4
GPQA Diamond60.5%35.7%
LMArena Expert13571211
Vectara Hallucination Rate9.3%—
MMLU—86.4%
TriviaQA—84.8%

Multilingual GLM-4.7-Flash leads

GLM-4.7-Flash: 46.8 (#152), GPT-4: 40.8 (#210)

BenchmarkGLM-4.7-FlashGPT-4
LMArena Non-English13311246
LMArena Chinese14031242
LMArena French13321282
LMArena German13361251
LMArena Korean12841184
LMArena Russian13331251
LMArena Spanish13511261
LMArena Japanese—1209

Instruction Following GLM-4.7-Flash leads

GLM-4.7-Flash: 70.3 (#162), GPT-4: 65.5 (#217)

BenchmarkGLM-4.7-FlashGPT-4
LMArena Instruction Following13271241

Long Context GLM-4.7-Flash leads

GLM-4.7-Flash: 40.9 (#143), GPT-4: 37.7 (#207)

BenchmarkGLM-4.7-FlashGPT-4
LMArena Longer Query13451244

Writing & Preference GLM-4.7-Flash leads

GLM-4.7-Flash: 47.7 (#206), GPT-4: 35.0 (#263)

BenchmarkGLM-4.7-FlashGPT-4
LMArena Text13511263
LMArena Creative Writing12971244
EQ-Bench Creative Writing1125752
LMArena Multi-Turn13421257

Frequently asked questions

Is GLM-4.7-Flash better than GPT-4?

GLM-4.7-Flash is the stronger model overall, scoring 38.4 to 28.9 on the Noometry Index.

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

GLM-4.7-Flash is cheaper. It lists at $0.06 per million input tokens and $0.40 per million output tokens; GPT-4 lists at $30 and $60.

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

GLM-4.7-Flash scores higher on coding benchmarks: 40.0 versus 31.2 in the Noometry coding category.

Which has the bigger context window?

GLM-4.7-Flash does, with 200K tokens against 8K.

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

20 benchmarks have published results for both models. GLM-4.7-Flash has 21 scored results on Noometry and GPT-4 has 38.

Related comparisons

Go deeper