Compare AI models

Specifications
Parameters
—744B
API pricing
Input price
$5.00$1.00
Output price
$25.00$3.20
Cached input price
$0.50$0.20
Cheapest input
$5.00Amazon Bedrock$0.60GMICloud
Cheapest output
$25.00Amazon Bedrock$1.92GMICloud
Benchmarks
BullshitBench v2
90%28%
SWE-Bench Verified
80.9%77.8%
Humanity's Last Exam · with tools
30.8%50.4%
GPQA Diamond
87%86%
Overview
CompanyAnthropicZ.ai
Release dateNov 24 2025Feb 12 2026
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

Claude Opus 4.5 leads GLM-5 on 3 of the 4 benchmarks they both report (BullshitBench v2, SWE-Bench Verified, Humanity's Last Exam, GPQA Diamond). GLM-5 is cheaper on both input and output: $1.00 vs $5.00 per million input tokens, and $3.20 vs $25.00 per million output tokens. Claude Opus 4.5 shipped 80 days before GLM-5, so benchmark comparisons should account for the intervening progress.

Claude Opus 4.5 is closed, while GLM-5 is open weight.

On BullshitBench v2, Claude Opus 4.5 leads at 90% vs GLM-5 at 28%. On SWE-Bench Verified, Claude Opus 4.5 leads at 80.9% vs GLM-5 at 77.8%. On Humanity's Last Exam · with tools, GLM-5 leads at 50.4% vs Claude Opus 4.5 at 30.8%. On GPQA Diamond, Claude Opus 4.5 leads at 87% vs GLM-5 at 86%.