Model comparison

GLM-5V-Turbo vs GPT-5.3 Codex

GPT-5.3 Codex is the stronger model overall, scoring 45.8 to 43.8 on the Noometry Index. GLM-5V-Turbo costs 2.5× less per token, which makes it the better buy when GPT-5.3 Codex's lead doesn't matter for your workload.

Last verified . 1 shared benchmarks.

GLM-5V-Turbo Z.ai (Zhipu)

43.8

Rank #84 Confirmed

GPT-5.3 Codex OpenAI

45.8

Rank #69 Reported

Summary

  • They share 1 benchmark with published results for both. GLM-5V-Turbo scores higher in 0 categories and GPT-5.3 Codex in 1 category; one gap is clear of the uncertainty.
  • The widest gap is in coding, where GPT-5.3 Codex leads 48.6 to 42.1.
  • GLM-5V-Turbo is cheaper at $1.20 / $4 per million input/output tokens, against $1.75 / $14 for GPT-5.3 Codex.
  • GPT-5.3 Codex accepts more context: 400K tokens versus 200K.

Side by side

GLM-5V-Turbo and GPT-5.3 Codex specifications
GLM-5V-TurboGPT-5.3 Codex
ProviderZ.ai (Zhipu)OpenAI
Noometry Index43.845.8
Released2026-04-012026-02-05
WeightsProprietaryProprietary
Context window200K400K
Max output131K128K
Input $ / M tokens$1.20$1.75
Output $ / M tokens$4$14
Results tracked198

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

Category by category

Coding GPT-5.3 Codex leads

GLM-5V-Turbo: 42.1 (#111), GPT-5.3 Codex: 48.6 (#56)

Coding benchmarks
BenchmarkGLM-5V-TurboGPT-5.3 Codex
LMArena WebDev14011409
SWE-bench Verified—74.8%
WeirdML—79.3%
LMArena Coding1466—
ALE-Bench—1,655

Agentic & Tool Use Not comparable

GLM-5V-Turbo: —, GPT-5.3 Codex: 48.0 (#9)

Agentic & Tool Use benchmarks
BenchmarkGLM-5V-TurboGPT-5.3 Codex
Terminal-Bench—78.4%
METR Time Horizons—74.5%
Vending-Bench 2—5,940

Reasoning Not comparable

GLM-5V-Turbo: 29.7 (#89), GPT-5.3 Codex: —

Reasoning benchmarks
BenchmarkGLM-5V-TurboGPT-5.3 Codex
LMArena Hard Prompts1443—
Epoch Capabilities Index—156.77

Math Not comparable

GLM-5V-Turbo: 39.4 (#106), GPT-5.3 Codex: —

Math benchmarks
BenchmarkGLM-5V-TurboGPT-5.3 Codex
LMArena Math1441—

Knowledge Not comparable

GLM-5V-Turbo: 40.6 (#117), GPT-5.3 Codex: —

Knowledge benchmarks
BenchmarkGLM-5V-TurboGPT-5.3 Codex
LMArena Expert1452—

Multimodal Not comparable

GLM-5V-Turbo: 40.9 (#42), GPT-5.3 Codex: —

Multimodal benchmarks
BenchmarkGLM-5V-TurboGPT-5.3 Codex
LMArena Vision1264—
LMArena Document1416—

Multilingual Not comparable

GLM-5V-Turbo: 53.0 (#73), GPT-5.3 Codex: —

Multilingual benchmarks
BenchmarkGLM-5V-TurboGPT-5.3 Codex
LMArena Non-English1420—
LMArena Chinese1488—
LMArena French1444—
LMArena German1423—
LMArena Korean1396—
LMArena Russian1431—
LMArena Spanish1450—

Instruction Following Not comparable

GLM-5V-Turbo: 75.0 (#80), GPT-5.3 Codex: —

Instruction Following benchmarks
BenchmarkGLM-5V-TurboGPT-5.3 Codex
LMArena Instruction Following1423—

Long Context Not comparable

GLM-5V-Turbo: 44.0 (#80), GPT-5.3 Codex: —

Long Context benchmarks
BenchmarkGLM-5V-TurboGPT-5.3 Codex
LMArena Longer Query1438—

Writing & Preference Not comparable

GLM-5V-Turbo: 62.5 (#73), GPT-5.3 Codex: —

Writing & Preference benchmarks
BenchmarkGLM-5V-TurboGPT-5.3 Codex
LMArena Text1437—
LMArena Creative Writing1416—
LMArena Multi-Turn1432—

Frequently asked questions

Is GLM-5V-Turbo better than GPT-5.3 Codex?

GPT-5.3 Codex is the stronger model overall, scoring 45.8 to 43.8 on the Noometry Index. GLM-5V-Turbo costs 2.5× less per token, which makes it the better buy when GPT-5.3 Codex's lead doesn't matter for your workload.

Which is cheaper, GLM-5V-Turbo or GPT-5.3 Codex?

GLM-5V-Turbo is cheaper. It lists at $1.20 per million input tokens and $4 per million output tokens; GPT-5.3 Codex lists at $1.75 and $14.

Is GLM-5V-Turbo or GPT-5.3 Codex better for coding?

GPT-5.3 Codex scores higher on coding benchmarks: 48.6 versus 42.1 in the Noometry coding category.

Which has the bigger context window?

GPT-5.3 Codex does, with 400K tokens against 200K.

How many benchmarks do GLM-5V-Turbo and GPT-5.3 Codex share?

1 benchmark has published results for both models. GLM-5V-Turbo has 19 scored results on Noometry and GPT-5.3 Codex has 8.

Related comparisons

Go deeper