We test ChatGPT, Gemini, Claude, Mistral and others on real Croatian legal questions — same questions, blind scoring, public results. Transparent: every answer with sources and each model's reasoning.
Open benchmark · verifiable methods · not legal advice
Benchmark · Phase 1
Leading AI systems on real Croatian legal questions, blind scoring of relevance and citation accuracy. Public and reproducible.
⏳ First results soon. Methodology public · these are placeholders, not real numbers.
Legal Intelligence
From the corpus we surface patterns no one publishes today — real success rates and odds. Examples (computed, not marketing):
Constitutional complaints upheld (odds 3.80). On the merits: 32.3% success.
Public bodies lose vs the Information Commissioner (odds 1.10).
Laws struck as unconstitutional (odds ~43). Rare but measurable.
Access to information: the citizen wins at the High Administrative Court (odds 5.49).
Judicial ethics (Supreme Court): complaint success (odds 28).
Argument patterns, articles cited in overturned judgments, change over time.
Computed over >16,000 decisions; methodology and CSVs available. Not legal advice or outcome prediction.
Live demo
Searches the corpus and returns relevant decisions with sources and a score. Demo over a limited corpus; not legal advice.
Upload with protection — unlike the others
Paste or load a document. A pseudo-anonymizer in your browser replaces personal data (national ID, IBAN, email, phone, names) before anything is sent onward. The mapping stays with you. Transparent — you see exactly what was removed.
Legislative Wayback Machine
Laws change. Lex-Rex reconstructs the text of provisions over time from the official gazette (ELI), so you know which wording of an article was in force on any date. Crucial when the outcome depends on the version that applied at the time.
What Lex-Rex is
Lex-Rex doesn't invent answers. It finds and cites real decisions and provisions, shows why they're relevant, and how confident it is. Lawyers and citizens alike get to the source fast — and can verify it.
Ask naturally — “Are repeated late arrivals grounds for extraordinary dismissal?” No boolean operators, no legalese required.
Every claim is tied to a specific decision or statutory article. No source — no claim.
Several independent AI models answer; the system reconciles them: agreement = confidence, disagreement = clearly flagged uncertainty.
Which version of an article was in force on a given date? Point-in-time view of legislation from the official gazette.
Starting with the Croatian corpus (case law, consolidated statutes, scholarship), designed to extend to other jurisdictions.
Methodology and benchmark are public. You can check how well the system actually retrieves the law.
How it works
A retrieval-augmented approach grounded in a real corpus, with model cross-checking.
In natural language — casual or formal.
Hybrid search (meaning + keywords) finds the most relevant decisions and provisions.
Multiple AI models answer independently; the system extracts consensus and flags disagreement.
Summary, citations, snippets and a confidence signal — ready to verify.
Why different
Lex-Rex Toolkit
A modular set of tools for working with your case file. The basics are free; advanced forensic processing and full-featured modules come with a paid plan.
Split, merge and compress PDFs — fast and local.
DOCX / ODF / images / HEIC → PDF, with merge into one document.
Resize/optimize images (e.g. for upload limits), batch.
Scanned files → searchable text; hearing audio/video → transcript.
Auto-download all filings per case from the court e-comms portal.
Upload your draft → multi-model review: checks citations against the corpus, structure, missing arguments, deadlines. Anonymized first. Not legal advice.
Forensic assembly: dedup, auto-pagination, index, chain-of-custody (SHA-256), citation graph and batch.
Pricing
Basic search and the public benchmark stay free. More models in the cross-check and the full Toolkit come with paid plans — you pay for depth of verification and advanced tools, not for "legal advice".
Prices indicative (TBD). Benchmark results stay free and public. "Not legal advice" applies on every tier.
Benchmark
Lex-Rex is built as an open benchmark: the same legal questions, public results, blind relevance evaluation. The goal is to let academia and the public test how well AI systems actually find and cite the law.
Leave your email — we'll reach out when the demo is ready and when we publish the first benchmark results.