Model comparison

GLM-4.7-Flash vs GPT-5.3 Codex

GPT-5.3 Codex is the stronger model overall, scoring 45.8 to 38.8 on the Noometry Index. GLM-4.7-Flash costs 33× less per token, which makes it the better buy when GPT-5.3 Codex's lead doesn't matter for your workload.

Last verified October 11, 2026. 0 shared benchmarks.

GLM-4.7-Flash Z.ai (Zhipu)

38.8

Rank #180 Confirmed

GPT-5.3 Codex OpenAI

45.8

Rank #69 Reported

Summary

The widest gap is in coding, where GPT-5.3 Codex leads 48.6 to 40.6.
GLM-4.7-Flash is cheaper at $0.06 / $0.40 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.
GLM-4.7-Flash has downloadable open weights; the other is API-only.

Side by side

GLM-4.7-Flash and GPT-5.3 Codex specifications
	GLM-4.7-Flash	GPT-5.3 Codex
Provider	Z.ai (Zhipu)	OpenAI
Noometry Index	38.8	45.8
Released	2026-01-19	2026-02-05
Weights	Open	Proprietary
Context window	200K	400K
Max output	131K	128K
Input $ / M tokens	$0.06	$1.75
Output $ / M tokens	$0.40	$14
Results tracked	21	8

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

Category by category

Coding GPT-5.3 Codex leads

GLM-4.7-Flash: 40.6 (#135), GPT-5.3 Codex: 48.6 (#56)

Coding benchmarks
Benchmark	GLM-4.7-Flash	GPT-5.3 Codex
SWE-bench Verified	—	74.8%
LMArena WebDev	—	1409
WeirdML	—	79.3%
LMArena Coding	1383	—
ALE-Bench	—	1,655

Agentic & Tool Use Not comparable

GLM-4.7-Flash: —, GPT-5.3 Codex: 48.0 (#9)

Agentic & Tool Use benchmarks
Benchmark	GLM-4.7-Flash	GPT-5.3 Codex
Terminal-Bench	—	78.4%
METR Time Horizons	—	74.5%
Vending-Bench 2	—	5,940

Reasoning Not comparable

GLM-4.7-Flash: 20.9 (#229), GPT-5.3 Codex: —

Reasoning benchmarks
Benchmark	GLM-4.7-Flash	GPT-5.3 Codex
Chess Puzzles	0%	—
LMArena Hard Prompts	1356	—
Epoch Capabilities Index	—	156.77

Math Not comparable

GLM-4.7-Flash: 36.1 (#173), GPT-5.3 Codex: —

Math benchmarks
Benchmark	GLM-4.7-Flash	GPT-5.3 Codex
OTIS Mock AIME 2024-2025	58.3%	—
LMArena Math	1355	—

Knowledge Not comparable

GLM-4.7-Flash: 35.5 (#184), GPT-5.3 Codex: —

Knowledge benchmarks
Benchmark	GLM-4.7-Flash	GPT-5.3 Codex
GPQA Diamond	60.5%	—
Vectara Hallucination Rate	9.3%	—
LMArena Expert	1357	—

Multilingual Not comparable

GLM-4.7-Flash: 46.5 (#158), GPT-5.3 Codex: —

Multilingual benchmarks
Benchmark	GLM-4.7-Flash	GPT-5.3 Codex
LMArena Non-English	1330	—
LMArena Chinese	1403	—
LMArena French	1332	—
LMArena German	1337	—
LMArena Korean	1283	—
LMArena Russian	1332	—
LMArena Spanish	1350	—

Instruction Following Not comparable

GLM-4.7-Flash: 70.1 (#167), GPT-5.3 Codex: —

Instruction Following benchmarks
Benchmark	GLM-4.7-Flash	GPT-5.3 Codex
LMArena Instruction Following	1327	—

Long Context Not comparable

GLM-4.7-Flash: 40.9 (#148), GPT-5.3 Codex: —

Long Context benchmarks
Benchmark	GLM-4.7-Flash	GPT-5.3 Codex
LMArena Longer Query	1345	—

Writing & Preference Not comparable

GLM-4.7-Flash: 47.4 (#210), GPT-5.3 Codex: —

Writing & Preference benchmarks
Benchmark	GLM-4.7-Flash	GPT-5.3 Codex
LMArena Text	1351	—
LMArena Creative Writing	1297	—
EQ-Bench Creative Writing	1125	—
LMArena Multi-Turn	1342	—

Frequently asked questions

Is GLM-4.7-Flash better than GPT-5.3 Codex?

Which is cheaper, GLM-4.7-Flash or GPT-5.3 Codex?

GLM-4.7-Flash is cheaper. It lists at $0.06 per million input tokens and $0.40 per million output tokens; GPT-5.3 Codex lists at $1.75 and $14.

Is GLM-4.7-Flash or GPT-5.3 Codex better for coding?

GPT-5.3 Codex scores higher on coding benchmarks: 48.6 versus 40.6 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-4.7-Flash and GPT-5.3 Codex share?

0 benchmarks have published results for both models. GLM-4.7-Flash has 21 scored results on Noometry and GPT-5.3 Codex has 8.