← Back to feed

New 'Access to Justice' Benchmark: Leading AI Models Miss Critical Legal Details

AI·评测 · 2026-11-14 14:10

A new "Access to Justice" benchmark evaluates 23 leading AI models on civil legal aid dialogues, revealing that even the top performer scored only 76.4%, falling short of the 80% reliability threshold and highlighting significant gaps in handling critical legal details.

Source: epyhia.com


Auto-generated summary for reference only. RSS