Step 2 of 4 · ProjectsBenchmarks
SARA
Statutory reasoning benchmark built on the US Internal Revenue Code.
What it does
A dataset for statutory reasoning: simplified sections of the US Internal Revenue Code paired with cases asking whether a section applies or how much tax is owed, plus a Prolog program that solves every case. Published as a paper, with data and code at nlp.jhu.edu/law, for language-understanding research. Simplified statutes mean answers differ from the current code; no licence is stated.
Where it fits on the map
On Learn
- BenchmarkGlossary term
- 04 · Evidence and reviewTrack
Similar projects
Of the same kind, for a shared jurisdiction or tax area. Not a ranking.
- harvey-labs (Legal Agent Benchmark)Legal Agent Benchmark: 2,010 legal tasks with documents and rubrics and a Python harness; 34 tasks are tax.
- LLM-Tax-AbuseCode and US tax-strategy data from the paper on whether LLMs can identify and generate tax abuse.
- PolicyBenchBenchmark of how well frontier AI models estimate household tax and benefit outcomes without tools.
- TaxCalcBenchBenchmark that tests frontier AI models on US tax return calculations.
- TaxBench114 expert-written US tax questions with grading rubrics for testing LLMs; 19 touch transfer pricing or s.482.Inactive since 2025
Maintain this project?
Link to this page from your README, so readers find the facts, the notes and where it fits. The badge is a small SVG served from this site.
[](https://tax-oss.com/projects/sara/)