The 2025 Vals Legal AI Report confirms Alexi’s leadership in accuracy, reliability, and compliance—outperforming lawyer and ChatGPT baselines in global benchmark tests.
As the legal world grapples with growing concerns over AI reliability, Alexi has emerged as a clear leader in independent testing. The Toronto-based legal intelligence platform has been validated in the 2025 Vals Legal AI Report (VLAIR)—one of the most rigorous evaluations of legal AI performance to date—confirming its advantages in accuracy, authoritative citations, and reliability.
Since May, there has been a 250% increase in cases of AI hallucinations in legal decisions worldwide, including 32 recorded incidents in Canada, prompting calls for higher standards in legal AI. The VLAIR study was developed to provide an objective, data-driven benchmark for assessing the accuracy, compliance, and performance of AI tools used by law firms.
The report found that Alexi:
- Scored 80% accuracy, outperforming a lawyer baseline of 71%—a 13% relative improvement.
- Tied for the highest score (79%) on single-jurisdiction legal issues, demonstrating best-in-class reasoning.
- Was 8% more likely than ChatGPT to cite valid primary law, reducing malpractice and compliance risk.
- Ranked among the top three performers for response speed, maintaining a 99% response rate compared to ChatGPT’s fourfold higher non-response rate.
“These results confirm what our customers experience every day: Alexi delivers the superior legal accuracy and compliance leading law firms need from AI, without compromising on speed or reliability,” said Mark Doble, CEO of Alexi. “As we look ahead, this validation cements our role in defining how the next generation of lawyers will work with precision, speed, and trust at scale.”
As law firms and regulators intensify scrutiny of AI-generated content, independent validation like VLAIR’s provides a new level of transparency in evaluating legal AI tools. For Alexi, the results reinforce its position as a trusted platform for the safe and efficient deployment of AI across legal research and automation.