Independent evaluation by Vals AI confirms superior accuracy and reliability of Jus AI 2

Jus Mundi commissioned AI benchmarking experts Vals.ai to conduct an independent evaluation of Jus AI 2 vs its original version.

International arbitration experts developed a comprehensive 60-question dataset covering a wide range of tasks typically undertaken by practicing lawyers. For each question, the experts specified criteria that a high-quality senior associate response should meet, for example including relevant cases references or understanding legal concepts in depth.

The evaluation confirms the significant advancement of Jus AI 2, which was preferred 5:1 over its original version and consistently outperformed its predecessor in relevance, correctness, and overall performance.

Download the benchmarking report to discover the complete findings and methodology.

ABOUT VALS AI

Vals AI is an independent AI evaluation platform specializing in benchmarking the performance of large language models across specialized professional domains. They are committed to advancing the future of Gen-AI through unbiased benchmarks and scalable evaluation infrastructure for labs and engineering teams.