Comparison · AI Models & LLMs

GPT-5.3-Codex vs GLM-5

The same method as our rankings: scores from the engine, sourced data, verified prices.

Details: GLM-5 →Details: GPT-5.3-Codex →

GLM-5

Z.ai

Full sheet →

71.3/100

SWE-bench accuracy: 72.8%
Context window: 200k tokens
Maximum output: 128k tokens
Input cost per 1M tokens: $1.00

GPT-5.3-Codex

OpenAI

Full sheet →

Context window: 400k tokens
Maximum output: 128k tokens
Input cost per 1M tokens: $1.75
Output cost per 1M tokens: $14.00

The numbers side by side

Each bar is the product's verified figure; on every row the longer bar is the higher of the two values.

Context windowhigher is better
GLM-5200k tokens
GPT-5.3-Codex400k tokens
Maximum outputhigher is better
GLM-5128k tokens
GPT-5.3-Codex128k tokens
Input cost per 1M tokenslower is better
GLM-5$1.00
GPT-5.3-Codex$1.75
Cached input cost per 1M tokenslower is better
GLM-5$0.20
GPT-5.3-Codex$0.175
Output cost per 1M tokenslower is better
GLM-5$3.20
GPT-5.3-Codex$14.00

Who wins where

For long documentsGPT-5.3-CodexContext window
Cheaper to readGLM-5Input cost per 1M tokens
Cheaper to writeGLM-5Output cost per 1M tokens

GPT-5.3-Codex: reads images · GLM-5: open weights (downloadable)

Data sheet side by side

Only the differences (10)

Performance

SWE-bench accuracy72.8%Not stated

Memory and answer length

Context window200k tokens✓400k tokens100% more

Maximum output128k tokens128k tokens

API prices

Input cost per 1M tokens✓$1.0043% less$1.75

Cached input cost per 1M tokens$0.20✓$0.17513% less

Output cost per 1M tokens✓$3.2077% less$14.00

Knowledge and abilities

Knowledge cutoffNot statedAugust 2025

Reads imagesNot statedYes

Size and openness

Parameters744 billionNot stated

Active parameters per token40 billionNot stated

Open weights (downloadable)YesNot stated

What a month costs

Change the volumes: the cost is worked out from the verified list prices above.

Million tokens read per monthMillion tokens written per monthShare of the input served from cache: 0%

GLM-5$3.60per month · $43.20 per yearThe cheaper one — you save $6.90 per month

GPT-5.3-Codex$10.50per month · $126 per year

The scenarios are only starting points to edit, not data about your use. List prices without discounts, time-of-day rates or taxes.

Questions and answers

For long documents: GLM-5 or GPT-5.3-Codex?

GPT-5.3-Codex: 400k tokens against 200k tokens (Context window).

Cheaper to read: GLM-5 or GPT-5.3-Codex?

GLM-5: $1.00 against $1.75 (Input cost per 1M tokens).

Cheaper to write: GLM-5 or GPT-5.3-Codex?

GLM-5: $3.20 against $14.00 (Output cost per 1M tokens).

Compare other products