Noometry

Model comparison

GLM-5.3-Flash vs GPT-5.2 Codex

GLM-5.3-Flash is the stronger model overall, scoring 51.8 to 42.6 on the Noometry Index.

Last verified . 2 shared benchmarks.

GLM-5.3-Flash Z.ai (Zhipu)

51.8

Rank #41 Confirmed

GPT-5.2 Codex OpenAI

42.6

Rank #111 Reported

Summary

  • They share 2 benchmarks with published results for both. GLM-5.3-Flash scores higher in 1 category and GPT-5.2 Codex in 1 category; 2 gaps are clear of the uncertainty.
  • The widest gap is in coding, where GLM-5.3-Flash leads 53.1 to 45.5.
  • GLM-5.3-Flash is cheaper at $0.15 / $0.50 per million input/output tokens, against $1.75 / $14 for GPT-5.2 Codex.
  • GLM-5.3-Flash accepts more context: 1M tokens versus 400K.
  • GLM-5.3-Flash has downloadable open weights; the other is API-only.

Side by side

GLM-5.3-FlashGPT-5.2 Codex
ProviderZ.ai (Zhipu)OpenAI
Noometry Index51.842.6
Released2026-08-202025-12-18
WeightsOpenProprietary
Context window1M400K
Max output131K128K
Input $ / M tokens$0.15$1.75
Output $ / M tokens$0.50$14
Results tracked405

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

Category by category

Coding GLM-5.3-Flash leads

GLM-5.3-Flash: 53.1 (#31), GPT-5.2 Codex: 45.5 (#71)

BenchmarkGLM-5.3-FlashGPT-5.2 Codex
LMArena WebDev16091339
ALE-Bench303.551,300
DeepSWE63.4%—
FrontierCode31.8%—
SWE-bench Verified (bash only)—72.8%
CursorBench36.8%—
SWE-bench Multilingual—66.3%
FrontierSWE18.1%—
SciCode51.6%—
LMArena Coding1508—

Agentic & Tool Use GPT-5.2 Codex leads

GLM-5.3-Flash: 34.2 (#47), GPT-5.2 Codex: 41.0 (#22)

BenchmarkGLM-5.3-FlashGPT-5.2 Codex
Terminal-Bench—66.5%
APEX-Agents52.8%—
GDP.pdf14%—

Reasoning Not comparable

GLM-5.3-Flash: 48.0 (#42), GPT-5.2 Codex: —

BenchmarkGLM-5.3-FlashGPT-5.2 Codex
ARC-AGI-265.8%—
ARC-AGI-191%—
CritPt15.4%—
Chess Puzzles14%—
LMArena Hard Prompts1491—
Mystery Game Puzzles8%—
Surface Evolver Bench52.5%—
Bench to the Future 30.15—
Epoch Capabilities Index151.88—

Math Not comparable

GLM-5.3-Flash: 53.3 (#47), GPT-5.2 Codex: —

BenchmarkGLM-5.3-FlashGPT-5.2 Codex
FrontierMath (Tiers 1-3)55.8%—
FrontierMath Tier 417.1%—
OTIS Mock AIME 2024-202593.9%—
ProofBench21%—
LMArena Math1500—

Knowledge Not comparable

GLM-5.3-Flash: 58.4 (#36), GPT-5.2 Codex: —

BenchmarkGLM-5.3-FlashGPT-5.2 Codex
GPQA Diamond90.2%—
LMArena Expert1513—

Multimodal Not comparable

GLM-5.3-Flash: 42.8 (#27), GPT-5.2 Codex: —

BenchmarkGLM-5.3-FlashGPT-5.2 Codex
LMArena Vision1296—

Multilingual Not comparable

GLM-5.3-Flash: 56.0 (#25), GPT-5.2 Codex: —

BenchmarkGLM-5.3-FlashGPT-5.2 Codex
LMArena Non-English1462—
LMArena Chinese1527—
LMArena French1496—
LMArena German1470—
LMArena Japanese1429—
LMArena Korean1446—
LMArena Russian1469—
LMArena Spanish1471—

Instruction Following Not comparable

GLM-5.3-Flash: 77.5 (#20), GPT-5.2 Codex: —

BenchmarkGLM-5.3-FlashGPT-5.2 Codex
LMArena Instruction Following1478—

Long Context Not comparable

GLM-5.3-Flash: 45.4 (#39), GPT-5.2 Codex: —

BenchmarkGLM-5.3-FlashGPT-5.2 Codex
LMArena Longer Query1482—

Writing & Preference Not comparable

GLM-5.3-Flash: 65.3 (#50), GPT-5.2 Codex: —

BenchmarkGLM-5.3-FlashGPT-5.2 Codex
LMArena Text1471—
LMArena Creative Writing1442—
LMArena Multi-Turn1467—

Frequently asked questions

Is GLM-5.3-Flash better than GPT-5.2 Codex?

GLM-5.3-Flash is the stronger model overall, scoring 51.8 to 42.6 on the Noometry Index.

Which is cheaper, GLM-5.3-Flash or GPT-5.2 Codex?

GLM-5.3-Flash is cheaper. It lists at $0.15 per million input tokens and $0.50 per million output tokens; GPT-5.2 Codex lists at $1.75 and $14.

Is GLM-5.3-Flash or GPT-5.2 Codex better for coding?

GLM-5.3-Flash scores higher on coding benchmarks: 53.1 versus 45.5 in the Noometry coding category.

Which has the bigger context window?

GLM-5.3-Flash does, with 1M tokens against 400K.

How many benchmarks do GLM-5.3-Flash and GPT-5.2 Codex share?

2 benchmarks have published results for both models. GLM-5.3-Flash has 40 scored results on Noometry and GPT-5.2 Codex has 5.

Related comparisons

Go deeper