# TaxEval v2 — AI model rankings

A set of real tax questions created by Vals AI — can the AI give accurate answers about tax rules and filings? Higher is better.

4 tracked models have a published TaxEval v2 score. Higher is better. Scores are as published at each model's release.

## Ranking

| Rank | Model | Developer | Score | Released |
| --- | --- | --- | --- | --- |
| 1 | Muse Spark 1.1 | Meta | 79.72% | Jul 9 2026 |
| 2 | Claude Fable 5 | Anthropic | 76.94% | Jun 9 2026 |
| 3 | Claude Opus 4.8 | Anthropic | 75.63% | May 28 2026 |
| 4 | GPT-5.5 | OpenAI | 74.98% | Apr 23 2026 |


---

Canonical page: https://aireleasetracker.com/benchmark/taxeval-v2
Full dataset: https://aireleasetracker.com/llms-full.txt · JSON: https://aireleasetracker.com/models.json
Source: AI Release Tracker (https://aireleasetracker.com). Benchmark scores are the figures published by the releasing lab at launch.