Leaderboard, made by Vals AI
TaxEval v2
Hard tax questions, created with financial and tax experts. Scores answer correctness and stepwise reasoning against expert reasoning.
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 |