Test design

The evaluation used a fixed, stratified set of U.S. federal tax questions. Each question was answered twice by the same model: once without TaxMCP and once with TaxMCP connected. The paired design was intended to isolate the effect of access to retrieved primary authority.

Answers were graded against primary tax authority. The published homepage examples cover the post-OBBBA interest-limitation basis under IRC §163(j), the 2026 information-reporting threshold under §6041, and the bonus-depreciation rule under §168(k).

Metric definitions

Reported results

The TaxMCP-assisted run received a 9.8/10 mean overall grade versus 7.4 without retrieval, and was right or tied on 93% of questions. It scored 10/10 on the recent-law subset versus 4.8 without TaxMCP. The assisted answers were free of critical errors 96.7% of the time and stated evaluated figures and dates correctly 99.3% of the time.

How to read the results

This paired benchmark measures the effect of TaxMCP retrieval on a fixed set of federal tax questions. With TaxMCP connected, the model's mean accuracy grade rose from 7.4 to 9.8 and its recent-law score rose from 4.8 to 10.

Model behavior, source coverage, prompting, and tax law can change. That is why TaxMCP returns linked authority: every production answer can be checked against the underlying source by the professional responsible for the conclusion.

What comes next

Future editions will expand the benchmark with repeated runs, a published de-identified question set and grading rubric, versioned model details, preserved outputs, and external tax-practitioner review.