A new benchmark for Dutch legal AI, DELTA, is expanding how legal AI is evaluated by measuring not only whether an answer is correct, but whether it is usable as written. Led by independent research organisation Legal Benchmarks with Zeno as Founding Research Partner, DELTA scores outputs across three dimensions: substance, citation, and form, with the last closest to what the wider AI industry has begun calling “taste.” Its accompanying survey of 115 legal professionals across 12 Dutch law firms found that only 32.2% usually receive a usable answer from an AI tool on the first prompt. The remaining 67.8% needed follow-up prompts, corrections, or additional research before the output was ready to rely on.
Click here for the official case/release
Disclaimer
The Legal Wire takes all necessary precautions to ensure that the materials, information, and documents on its website, including but not limited to articles, newsletters, reports, and blogs (“Materials”), are accurate and complete. Nevertheless, these Materials are intended solely for general informational purposes and do not constitute legal advice. They may not necessarily reflect the current laws or regulations. The Materials should not be interpreted as legal advice on any specific matter. Furthermore, the content and interpretation of the Materials and the laws discussed within are subject to change.
