Z.ai's GLM-Legal scores 19.17% on Harvey LAB, nearly tripling its base model
AIZ.ai releases GLM-Legal, a legal AI model built on GLM-5.3-Flash, which scores 19.17% on Harvey's Legal Agent Benchmark, up from 6.67% for its base model, according to Vals AI's runs. It ranks #7 of 79 on the Vals AI leaderboard at $0.15 per test, versus $19.23 for Claude Fable 5.
Source details
MarkTechPost · Michal Sutter · marktechpost.comPublished · added here
Original title: Z.ai GLM-Legal Beats Claude Fable 5 and Kimi K3 on Harvey LAB