Noometry

Model comparison

GLM-4.6V vs GPT-4 Turbo

GLM-4.6V is the stronger model overall, scoring 41.3 to 30.5 on the Noometry Index.

Last verified . 12 shared benchmarks.

GLM-4.6V Z.ai (Zhipu)

41.3

Rank #137 Confirmed

GPT-4 Turbo OpenAI

30.5

Rank #292 Confirmed

Summary

  • They share 12 benchmarks with published results for both. GLM-4.6V scores higher in 8 categories and GPT-4 Turbo in 0 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where GLM-4.6V leads 38.0 to 24.3.
  • GLM-4.6V is cheaper at $0.30 / $0.90 per million input/output tokens, against $10 / $30 for GPT-4 Turbo.
  • GLM-4.6V has downloadable open weights; the other is API-only.

Side by side

GLM-4.6VGPT-4 Turbo
ProviderZ.ai (Zhipu)OpenAI
Noometry Index41.330.5
Released2025-12-082023-11-06
WeightsOpenProprietary
Context window128K128K
Max output33K4K
Input $ / M tokens$0.30$10
Output $ / M tokens$0.90$30
Results tracked1236

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 Turbo: 33.8 (#249)

BenchmarkGLM-4.6VGPT-4 Turbo
LMArena Coding13901268
WeirdML—18%
BigCodeBench Instruct—48.2%
BigCodeBench Complete—58.2%
HumanEval+—86.6%
MBPP+—73.3%

Agentic & Tool Use Not comparable

GLM-4.6V: —, GPT-4 Turbo: —

BenchmarkGLM-4.6VGPT-4 Turbo
METR Time Horizons—36.7%

Reasoning GLM-4.6V leads

GLM-4.6V: 27.6 (#115), GPT-4 Turbo: 15.3 (#317)

BenchmarkGLM-4.6VGPT-4 Turbo
LMArena Hard Prompts13681251
SimpleBench—25.1%
Chess Puzzles—6%
DTBench—61.6%
LMCA—9.8%
Epoch Capabilities Index—127.25
ForecastBench—59.4

Math Not comparable

GLM-4.6V: —, GPT-4 Turbo: 9.0 (#322)

BenchmarkGLM-4.6VGPT-4 Turbo
FrontierMath (Tiers 1-3)—0.7%
OTIS Mock AIME 2024-2025—6.7%
LMArena Math—1272
MATH Level 5—46.7%

Knowledge GLM-4.6V leads

GLM-4.6V: 38.0 (#149), GPT-4 Turbo: 24.3 (#268)

BenchmarkGLM-4.6VGPT-4 Turbo
LMArena Expert13711223
GPQA Diamond—46.6%
Confabulations—28.4%
MMLU—81.3%

Multimodal GLM-4.6V leads

GLM-4.6V: 34.8 (#90), GPT-4 Turbo: 30.6 (#110)

BenchmarkGLM-4.6VGPT-4 Turbo
LMArena Vision11641090

Multilingual GLM-4.6V leads

GLM-4.6V: 48.6 (#141), GPT-4 Turbo: 40.5 (#216)

BenchmarkGLM-4.6VGPT-4 Turbo
LMArena Non-English13591245
LMArena Chinese14251242
LMArena Russian13401259
LMArena French—1276
LMArena German—1259
LMArena Japanese—1194
LMArena Korean—1187
LMArena Spanish—1260

Instruction Following GLM-4.6V leads

GLM-4.6V: 71.4 (#151), GPT-4 Turbo: 65.8 (#216)

BenchmarkGLM-4.6VGPT-4 Turbo
LMArena Instruction Following13521249

Long Context GLM-4.6V leads

GLM-4.6V: 41.3 (#143), GPT-4 Turbo: 38.0 (#206)

BenchmarkGLM-4.6VGPT-4 Turbo
LMArena Longer Query13581254

Writing & Preference GLM-4.6V leads

GLM-4.6V: 56.6 (#137), GPT-4 Turbo: 47.7 (#206)

BenchmarkGLM-4.6VGPT-4 Turbo
LMArena Text13771272
LMArena Creative Writing13471269
LMArena Multi-Turn13601267

Frequently asked questions

Is GLM-4.6V better than GPT-4 Turbo?

GLM-4.6V is the stronger model overall, scoring 41.3 to 30.5 on the Noometry Index.

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

GLM-4.6V is cheaper. It lists at $0.30 per million input tokens and $0.90 per million output tokens; GPT-4 Turbo lists at $10 and $30.

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

GLM-4.6V scores higher on coding benchmarks: 40.9 versus 33.8 in the Noometry coding category.

Which has the bigger context window?

Both accept 128K tokens.

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

12 benchmarks have published results for both models. GLM-4.6V has 12 scored results on Noometry and GPT-4 Turbo has 36.

Related comparisons

Go deeper