Compare AI models

Specifications
Parameters
—744B
API pricing
Input price
$1.75$1.00
Output price
$14.00$3.20
Cached input price
$0.175$0.20
Cheapest input
$1.75Azure$0.60GMICloud
Cheapest output
$14.00Azure$1.92GMICloud
Benchmarks
BullshitBench v2
24%28%
SWE-Bench Verified
85%77.8%
Overview
CompanyOpenAIZ.ai
Release dateFeb 5 2026Feb 12 2026
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

GPT-5.3-Codex and GLM-5 are evenly matched across the 2 benchmarks they both report (BullshitBench v2, SWE-Bench Verified). GLM-5 is cheaper on both input and output: $1.00 vs $1.75 per million input tokens, and $3.20 vs $14.00 per million output tokens. GPT-5.3-Codex shipped 7 days before GLM-5, so benchmark comparisons should account for the intervening progress.

GPT-5.3-Codex is closed, while GLM-5 is open weight.

On BullshitBench v2, GLM-5 leads at 28% vs GPT-5.3-Codex at 24%. On SWE-Bench Verified, GPT-5.3-Codex leads at 85% vs GLM-5 at 77.8%.