Sign in

TaxEval

As of Nov 3, 2026, TaxEval (v2) is maintained by Vals AI. Metric accuracy (%). Ceiling 100. Saturation unknown. Contamination risk low.

Maintainer
Vals AI
Metric
accuracy (%)
Ceiling
100
Saturation
unknown
Contamination
low
Cadence
Declared cadence: as Vals updates (checked daily). Catalog snapshots: 1, latest Oct 27, 2026.
Source
Vals AI · this benchmark on Vals AI
Grading
AI judge (LLM-graded rubric) — Answer correctness and stepwise reasoning are graded by an LLM judge.

Source: Vals AI. A proprietary private test set run by Vals; scores are republished with permission. Rows are dated the day isitsota first saw them, and only the benchmark's standard harness counts.

Categories

Where it counts

Top 5

Current top scores

  1. Muse Spark 1.2 · 80.376 · Oct 27, 2026
  2. Muse Spark 1.1 · 79.722 · Oct 27, 2026
  3. Muse Spark · 77.678 · Oct 27, 2026
  4. Claude Sonnet 4.6 · 77.106 · Oct 27, 2026
  5. Claude Fable 5 · 76.942 · Oct 27, 2026
ModelScoreDateKind
Muse Spark 1.280.3762026-10-27snapshot
Muse Spark 1.179.7222026-10-27snapshot
Muse Spark77.6782026-10-27snapshot
Claude Sonnet 4.677.1062026-10-27snapshot
Claude Fable 576.9422026-10-27snapshot
GPT-5.6 Terra76.1662026-10-27snapshot
GPT-5.6 Luna76.1662026-10-27snapshot
Claude Opus 4.6 Thinking75.9612026-10-27snapshot
Claude Fable 5.175.9612026-10-27snapshot
Grok 375.8792026-10-27snapshot
GPT-5.275.7562026-10-27snapshot
Kimi K375.7162026-10-27snapshot
Grok 4 Fast Reasoning75.6972026-10-27snapshot
Claude Opus 4.875.6342026-10-27snapshot
Claude Sonnet 575.6342026-10-27snapshot
GLM 5.3 Flash75.5932026-10-27snapshot
Qwen3 8 Max75.5522026-10-27snapshot
Inkling Small75.5112026-10-27snapshot
Qwen3 7 Max75.3062026-10-27snapshot
Inkling75.3062026-10-27snapshot
Claude Opus 4.775.2662026-10-27snapshot
GPT-5 Mini75.2252026-10-27snapshot
Claude Opus 575.1432026-10-27snapshot
GPT-4.175.0612026-10-27snapshot
GPT-5.574.982026-10-27snapshot
Gemini 3.6 Flash74.8572026-10-27snapshot
GPT-5.174.8572026-10-27snapshot
Claude Opus 4.5 20251101 Thinking74.8562026-10-27snapshot
o4-mini74.7762026-10-27snapshot
GPT-5.6 Sol74.7752026-10-27snapshot