Step 2 of 4 · ProjectsBy kind

Benchmarks: 9 open source projects.

Evals that show whether a model reasons about tax, or guesses.

9 projects8 maintained7 on the map2 jurisdictions + globalFacts checked 6 Oct 2026

Browse these by tax area

Income tax Corporate tax Benefits VAT & indirect Cross-cutting

harvey-labs (Legal Agent Benchmark)Legal Agent Benchmark: 2,010 legal tasks with documents and rubrics and a Python harness; 34 tasks are tax.BenchmarkUS

HSCodeCompExpert-level benchmark for HS code classification agents on e-commerce products, from Alibaba's MarcoPolo.BenchmarkGlobal

Legora transfer pricing caseEvaluation case for AI: draft a transfer pricing Master File from case documents, graded on 175 criteria.BenchmarkGlobal

LLM-Tax-AbuseCode and US tax-strategy data from the paper on whether LLMs can identify and generate tax abuse.BenchmarkUSLicence unknown

PolicyBenchBenchmark of how well frontier AI models estimate household tax and benefit outcomes without tools.BenchmarkGlobal

SARAStatutory reasoning benchmark built on the US Internal Revenue Code.BenchmarkUS

TaxCalcBenchBenchmark that tests frontier AI models on US tax return calculations.BenchmarkUS

TaxBench114 expert-written US tax questions with grading rubrics for testing LLMs; 19 touch transfer pricing or s.482.BenchmarkUSInactive since 2025

UK Trade Tariff AI search evaluation suiteEvaluation suite for the UK tariff team's AI classification and search experiments on the Online Trade Tariff.BenchmarkUKDemo

Labels mark what to check before you rely on an entry: inactive or archived code, demos, paid services and unclear licences. Only maintained projects for companies and tax authorities appear on the map. Search and filter the whole list.

Missing a project? Add it to the list.

Submit a project

Next · Step 3 of 4The gapsThe activities with no open project yet, and the partly covered ones, with what to build on.