Alexi is a legal AI vendor founded in 2017 that is focused on streamlining workflows for legal teams and in-house counsel. In the VLAIR legal research study, their research product, which has been trained on case law, achieved strong performance across all evaluation criteria, matching the highest accuracy score among all participants.

Performance Summary

Alexi was evaluated on legal research capabilities across 200 U.S. legal research questions, with responses scored on three weighted criteria: accuracy (50% weight), authoritativeness (40% weight), and appropriateness (10% weight).

Alexi demonstrated strong performance across all evaluated criteria, achieving 80% accuracy, 75% authoritativeness, and 70% appropriateness, resulting in a 77% aggregate weighted score.

Key Strengths

Based on VLAIR evaluation results, Alexi demonstrates several notable capabilities:

1. Top-tier accuracy: Achieved 80% accuracy, tying for the highest accuracy score among all participants in the study, demonstrating exceptional capability in providing substantively correct responses with minimal misinterpretations or factual errors.

2. Strong authoritativeness: Scored 75% on authoritativeness, placing second among all participants in identifying and citing relevant and valid primary law sources, significantly outperforming the lawyer baseline by 7 percentage points.

3. Case law expertise: Built on a foundation of training specifically on case law, enabling strong performance on questions requiring identification and analysis of judicial decisions and precedents.

4. Comprehensive legal coverage: Successfully provided responses to 198 of 200 questions, with only 2 instances where the product acknowledged it was unable to locate the right documents but still provided some form of response or explanation.

5. In-house counsel optimization: Designed specifically to streamline workflows for legal teams and in-house counsel, providing responses tailored to the practical needs of these user groups.

6. Consistent above-baseline performance: Outperformed the lawyer baseline across all three scoring criteria (accuracy, authoritativeness, and appropriateness), demonstrating the ability to augment and enhance legal research capabilities for practicing attorneys.

7. Strong appropriateness scores: Achieved 70% on appropriateness, indicating responses are generally well-formatted, easy to understand, and suitable for sharing with colleagues or clients with minimal revision.

Based on the Vals Legal AI Report (VLAIR) - Legal Research, October 2025 - Independent benchmarking study of legal AI products on U.S. legal research questions contributed by Am Law 100 law firms.