# Tax Agent Bench leaderboard

external benchmark

> Every figure below is reproduced as its upstream source published it: nothing is modelled, estimated, interpolated or converted. `Unavailable` means no source published the value — it is never a zero. Each value carries its evidence state and the date it was observed.

Page: https://modelscale.dev/leaderboards/benchmarks/external-vals-tax-agent-bench

Vals Tax Agent Bench. Every model the catalog carries a published Tax Agent Bench value for, ranked by that value.

## Benchmark record

| Field | Value |
| --- | --- |
| Category | external |
| Measure | Citation-adjusted all-pass accuracy; Weighted Pass separate |
| Tasks | 193 private US tax test questions across six categories |
| Difficulty | Research-grade US tax questions |
| Published by | [Tax Agent Bench](https://www.vals.ai/benchmarks/tax_agent_bench) |

Agent evaluation on research-grade US tax questions using the Tax Agent Bench harness.

## Tax Agent Bench ranking

No model in the catalog has a published Tax Agent Bench score. The benchmark is defined by Tax Agent Bench, but the catalog carries no value for it yet. An absent value is shown as absent here rather than as a zero.

Rows are ordered by the value the source published, highest first. The source does not state whether a higher value is the better result, so this document does not either: for a benchmark that measures a rate of failure, read the table from the bottom.
