Vals AI
TaxEval v2
Hard tax questions, created with financial and tax experts. Scores answer correctness and stepwise reasoning against expert reasoning.
About this benchmark
- Size
- Over 1,500 questions (20 public validation, 300 private validation, 1,223 test)
- Public split
- No public download; validation sets are available on request or for purchase
- Grading
- Accuracy, judged by an LLM (Claude Sonnet 4.5, non-thinking, since 17 Nov 2025; Claude 3.5 Sonnet before).
- Licence
- proprietary
- Submission
- Not stated
- Products allowed
- Not stated
- Latest version
- v2
- What it does not cover
- Archived as saturated: no longer run on new models. No tool use, retrieval or citations (see Tax Agent Bench for agentic tax research).
Results
5 modelsEach score shows who reported it: the benchmark's authors (quoted from their paper), the benchmark's official board, or Moneda (run with the benchmark's own grader and rules). We do not copy other aggregators.
TaxEval v2 v2
accuracy % (v2), higher is better. 5 models.
Updated 1 Sept 2026
- Muse Spark 1.280.4
- Muse Spark 1.179.7
- Muse Spark77.7
- Claude Sonnet 4.677.1
- Claude Fable 576.9
TaxEval v2 v2
accuracy % (v2), higher is better. 5 models.
Updated 1 Sept 2026
- 1Muse Spark 1.280.4
- 2Muse Spark 1.179.7
- 3Muse Spark77.7
- 4Claude Sonnet 4.677.1
- 5Claude Fable 576.9
| 1 | Muse Spark 1.2 | Meta | 80.4 | test set (1,223 questions), archived board | Vals.ai TaxEval v2 leaderboard Official board, reported 1 Sept 2026 · checked 2 Nov 2026 |
|---|---|---|---|---|---|
| 2 | Muse Spark 1.1 | Meta | 79.7 | test set (1,223 questions), archived board | Vals.ai TaxEval v2 leaderboard Official board, reported 1 Sept 2026 · checked 2 Nov 2026 |
| 3 | Muse Spark | Meta | 77.7 | test set (1,223 questions), archived board | Vals.ai TaxEval v2 leaderboard Official board, reported 1 Sept 2026 · checked 2 Nov 2026 |
| 4 | Claude Sonnet 4.6 | Anthropic | 77.1 | test set (1,223 questions), archived board | Vals.ai TaxEval v2 leaderboard Official board, reported 1 Sept 2026 · checked 2 Nov 2026 |
| 5 | Claude Fable 5 | Anthropic | 76.9 | test set (1,223 questions), archived board | Vals.ai TaxEval v2 leaderboard Official board, reported 1 Sept 2026 · checked 2 Nov 2026 |
Papers and links
Last checked 2 Nov 2026. Something out of date or wrong? Send a correction.