Tax questions
TaxEval v2
A set of real tax questions created by Vals AI — can the AI give accurate answers about tax rules and filings? Higher is better.
Rankings
Higher is betterTaxEval v2 — frequently asked questions
- What is TaxEval v2?
- A set of real tax questions created by Vals AI — can the AI give accurate answers about tax rules and filings? Higher is better.
- Which AI model scores highest on TaxEval v2?
- Muse Spark 1.1 by Meta holds the best TaxEval v2 result among tracked models, at 79.72% (released Jul 9 2026). Higher scores are better on this benchmark.
- What are the top 4 models on TaxEval v2?
- 1. Muse Spark 1.1 (Meta) — 79.72%; 2. Claude Fable 5 (Anthropic) — 76.94%; 3. Claude Opus 4.8 (Anthropic) — 75.63%; 4. GPT-5.5 (OpenAI) — 74.98%.
- How many models have a published TaxEval v2 score?
- 4 tracked models have a published TaxEval v2 score. Scores are the figures reported by each lab at that model's release, so this page is a record of results over time rather than a re-run leaderboard.