Compare AI models

Specifications
Parameters
—744B
API pricing
Input price
$1.00$1.00
Output price
$5.00$3.20
Cached input price
$0.10$0.20
Cheapest input
$1.00Amazon Bedrock$0.60GMICloud
Cheapest output
$5.00Amazon Bedrock$1.92GMICloud
Benchmarks
BullshitBench v2
77%28%
SWE-Bench Verified
73.3%77.8%
GPQA Diamond
73%86%
Overview
CompanyAnthropicZ.ai
Release dateOct 15 2025Feb 12 2026
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

GLM-5 leads Claude Haiku 4.5 on 2 of the 3 benchmarks they both report (BullshitBench v2, SWE-Bench Verified, GPQA Diamond). Both charge $1.00 per million input tokens. GLM-5 is cheaper on output: $3.20 vs $5.00 per million tokens. Claude Haiku 4.5 shipped 120 days before GLM-5, so benchmark comparisons should account for the intervening progress.

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

On BullshitBench v2, Claude Haiku 4.5 leads at 77% vs GLM-5 at 28%. On SWE-Bench Verified, GLM-5 leads at 77.8% vs Claude Haiku 4.5 at 73.3%. On GPQA Diamond, GLM-5 leads at 86% vs Claude Haiku 4.5 at 73%.