Noometry

Model comparison

GLM-4.5-Air vs GPT-5.3 Codex

GPT-5.3 Codex is the stronger model overall, scoring 45.5 to 38.7 on the Noometry Index. GLM-4.5-Air costs 11× less per token, which makes it the better buy when GPT-5.3 Codex's lead doesn't matter for your workload.

Last verified . 0 shared benchmarks.

GLM-4.5-Air Z.ai (Zhipu)

38.7

Rank #169 Confirmed

GPT-5.3 Codex OpenAI

45.5

Rank #61 Reported

Summary

  • The widest gap is in coding, where GPT-5.3 Codex leads 48.5 to 34.5.
  • GLM-4.5-Air is cheaper at $0.20 / $1.10 per million input/output tokens, against $1.75 / $14 for GPT-5.3 Codex.
  • GPT-5.3 Codex accepts more context: 400K tokens versus 131K.
  • GLM-4.5-Air has downloadable open weights; the other is API-only.

Side by side

GLM-4.5-AirGPT-5.3 Codex
ProviderZ.ai (Zhipu)OpenAI
Noometry Index38.745.5
Released2025-07-202026-02-05
WeightsOpenProprietary
Context window131K400K
Max output98K128K
Input $ / M tokens$0.20$1.75
Output $ / M tokens$1.10$14
Results tracked278

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

Category by category

Coding GPT-5.3 Codex leads

GLM-4.5-Air: 34.5 (#225), GPT-5.3 Codex: 48.5 (#51)

BenchmarkGLM-4.5-AirGPT-5.3 Codex
SWE-bench Verified—74.8%
LMArena WebDev—1408
GSO2.9%—
WeirdML—79.3%
LMArena Coding1397—
ALE-Bench—1,655

Agentic & Tool Use Not comparable

GLM-4.5-Air: —, GPT-5.3 Codex: 47.8 (#9)

BenchmarkGLM-4.5-AirGPT-5.3 Codex
Terminal-Bench—78.4%
METR Time Horizons—74.5%
Vending-Bench 2—5,940

Reasoning Not comparable

GLM-4.5-Air: 23.3 (#166), GPT-5.3 Codex: —

BenchmarkGLM-4.5-AirGPT-5.3 Codex
Kagi LLM Benchmark43%—
LMArena Hard Prompts1379—
Epoch Capabilities Index—156.84
ForecastBench59.2—

Math Not comparable

GLM-4.5-Air: 33.8 (#166), GPT-5.3 Codex: —

BenchmarkGLM-4.5-AirGPT-5.3 Codex
Omni-MATH39.1%—
LMArena Math1396—

Knowledge Not comparable

GLM-4.5-Air: 34.6 (#184), GPT-5.3 Codex: —

BenchmarkGLM-4.5-AirGPT-5.3 Codex
Humanity's Last Exam8.1%—
MMLU-Pro76.2%—
Vectara Hallucination Rate9.3%—
GPQA (HELM)59.4%—
LMArena Expert1370—

Multilingual Not comparable

GLM-4.5-Air: 49.4 (#130), GPT-5.3 Codex: —

BenchmarkGLM-4.5-AirGPT-5.3 Codex
LMArena Non-English1366—
LMArena Chinese1427—
LMArena French1399—
LMArena German1376—
LMArena Japanese1348—
LMArena Korean1306—
LMArena Russian1373—
LMArena Spanish1385—

Instruction Following Not comparable

GLM-4.5-Air: 69.8 (#165), GPT-5.3 Codex: —

BenchmarkGLM-4.5-AirGPT-5.3 Codex
IFEval81.2%—
LMArena Instruction Following1353—

Long Context Not comparable

GLM-4.5-Air: 41.6 (#130), GPT-5.3 Codex: —

BenchmarkGLM-4.5-AirGPT-5.3 Codex
LMArena Longer Query1367—

Writing & Preference Not comparable

GLM-4.5-Air: 56.1 (#134), GPT-5.3 Codex: —

BenchmarkGLM-4.5-AirGPT-5.3 Codex
LMArena Text1384—
LMArena Creative Writing1343—
WildBench78.9%—
LMArena Multi-Turn1371—

Frequently asked questions

Is GLM-4.5-Air better than GPT-5.3 Codex?

GPT-5.3 Codex is the stronger model overall, scoring 45.5 to 38.7 on the Noometry Index. GLM-4.5-Air costs 11× 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-4.5-Air or GPT-5.3 Codex?

GLM-4.5-Air is cheaper. It lists at $0.20 per million input tokens and $1.10 per million output tokens; GPT-5.3 Codex lists at $1.75 and $14.

Is GLM-4.5-Air or GPT-5.3 Codex better for coding?

GPT-5.3 Codex scores higher on coding benchmarks: 48.5 versus 34.5 in the Noometry coding category.

Which has the bigger context window?

GPT-5.3 Codex does, with 400K tokens against 131K.

How many benchmarks do GLM-4.5-Air and GPT-5.3 Codex share?

0 benchmarks have published results for both models. GLM-4.5-Air has 27 scored results on Noometry and GPT-5.3 Codex has 8.

Related comparisons

Go deeper