A Canadian legal reasoning benchmark
CanLegal is an open evaluation benchmark measuring the legal-reasoning competence of large language models across Canadian case law, statutes, and regulations — bilingual, bijural, and built on a validated gold standard.
We'll only email you about the CanLegal release. Unsubscribe anytime. See our Privacy Policy.
What it measures
CanLegal tests the skills a legal professional actually relies on — statutory interpretation, outcome prediction, citation verification, and jurisdictional routing — across both of Canada's legal traditions and both official languages.
Every task carries explicit English/French and common-law/civil-law dimensions — the legal duality that defines Canadian law and that no other benchmark captures.
From statute and regulation interpretation to case-outcome prediction, citation verification, and jurisdiction routing — a broad surface of legal-reasoning skills.
A curated gold answer set, reviewed and validated through a multi-stage vetting process so scores reflect genuine legal competence, not annotation noise.
Tasks include perturbation and contamination safeguards that expose whether a model truly reasons or merely pattern-matches against memorized text.
Leading frontier models evaluated head-to-head on identical, closed-book prompts — a clean, comparable measure of Canadian legal reasoning.
No tools, no retrieval, no web access during evaluation — each model answers from its own learned knowledge, making results auditable and reproducible.
By the numbers
Get the public benchmark and leaderboard — straight to your inbox.
We'll only email you about the CanLegal release. Unsubscribe anytime. See our Privacy Policy.
CanLegal