Noometry

Model comparison

GLM-4.6V vs GPT-4

GLM-4.6V is the stronger model overall, scoring 41.3 to 29.1 on the Noometry Index.

Last verified . 11 shared benchmarks.

GLM-4.6V Z.ai (Zhipu)

41.3

Rank #137 Confirmed

GPT-4 OpenAI

29.1

Rank #316 Confirmed

Summary

  • They share 11 benchmarks with published results for both. GLM-4.6V scores higher in 7 categories and GPT-4 in 0 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in writing & preference, where GLM-4.6V leads 56.6 to 34.9.
  • GLM-4.6V is cheaper at $0.30 / $0.90 per million input/output tokens, against $30 / $60 for GPT-4.
  • GLM-4.6V accepts more context: 128K tokens versus 8K.
  • GLM-4.6V has downloadable open weights; the other is API-only.

Side by side

GLM-4.6VGPT-4
ProviderZ.ai (Zhipu)OpenAI
Noometry Index41.329.1
Released2025-12-082023-03-14
WeightsOpenProprietary
Context window128K8K
Max output33K8K
Input $ / M tokens$0.30$30
Output $ / M tokens$0.90$60
Results tracked1238

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

Category by category

Coding GLM-4.6V leads

GLM-4.6V: 40.9 (#128), GPT-4: 31.6 (#283)

BenchmarkGLM-4.6VGPT-4
LMArena Coding13901254
WeirdML—12.4%
BigCodeBench Instruct—46%
BigCodeBench Complete—57.2%
HumanEval+—79.3%

Agentic & Tool Use Not comparable

GLM-4.6V: —, GPT-4: —

BenchmarkGLM-4.6VGPT-4
METR Time Horizons—36.1%

Reasoning GLM-4.6V leads

GLM-4.6V: 27.6 (#115), GPT-4: 17.8 (#289)

BenchmarkGLM-4.6VGPT-4
LMArena Hard Prompts13681241
Chess Puzzles—4%
Mystery Game Puzzles—12%
DTBench—62.7%
LMCA—17.1%
BIG-Bench Hard—75.1%
Epoch Capabilities Index—125.89
ForecastBench—57.8
HellaSwag—95.3%
WinoGrande—87.5%

Math Not comparable

GLM-4.6V: —, GPT-4: 10.8 (#309)

BenchmarkGLM-4.6VGPT-4
OTIS Mock AIME 2024-2025—1.1%
LMArena Math—1269
MATH Level 5—23%
GSM8K—92%

Knowledge GLM-4.6V leads

GLM-4.6V: 38.0 (#149), GPT-4: 18.4 (#282)

BenchmarkGLM-4.6VGPT-4
LMArena Expert13711211
GPQA Diamond—35.7%
MMLU—86.4%
TriviaQA—84.8%

Multimodal Not comparable

GLM-4.6V: 34.8 (#90), GPT-4: —

BenchmarkGLM-4.6VGPT-4
LMArena Vision1164—

Multilingual GLM-4.6V leads

GLM-4.6V: 48.6 (#141), GPT-4: 40.6 (#215)

BenchmarkGLM-4.6VGPT-4
LMArena Non-English13591246
LMArena Chinese14251242
LMArena Russian13401251
LMArena French—1283
LMArena German—1251
LMArena Japanese—1209
LMArena Korean—1184
LMArena Spanish—1261

Instruction Following GLM-4.6V leads

GLM-4.6V: 71.4 (#151), GPT-4: 65.3 (#222)

BenchmarkGLM-4.6VGPT-4
LMArena Instruction Following13521241

Long Context GLM-4.6V leads

GLM-4.6V: 41.3 (#143), GPT-4: 37.7 (#212)

BenchmarkGLM-4.6VGPT-4
LMArena Longer Query13581244

Writing & Preference GLM-4.6V leads

GLM-4.6V: 56.6 (#137), GPT-4: 34.9 (#268)

BenchmarkGLM-4.6VGPT-4
LMArena Text13771263
LMArena Creative Writing13471244
LMArena Multi-Turn13601257
EQ-Bench Creative Writing—752

Frequently asked questions

Is GLM-4.6V better than GPT-4?

GLM-4.6V is the stronger model overall, scoring 41.3 to 29.1 on the Noometry Index.

Which is cheaper, GLM-4.6V or GPT-4?

GLM-4.6V is cheaper. It lists at $0.30 per million input tokens and $0.90 per million output tokens; GPT-4 lists at $30 and $60.

Is GLM-4.6V or GPT-4 better for coding?

GLM-4.6V scores higher on coding benchmarks: 40.9 versus 31.6 in the Noometry coding category.

Which has the bigger context window?

GLM-4.6V does, with 128K tokens against 8K.

How many benchmarks do GLM-4.6V and GPT-4 share?

11 benchmarks have published results for both models. GLM-4.6V has 12 scored results on Noometry and GPT-4 has 38.

Related comparisons

Go deeper