# Autoform-Hard 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://modelchoice.dev/leaderboards/benchmarks/external-vals-autoform-hard

Autoform-Hard (Vals AI). Every model the catalog carries a published Autoform-Hard value for, ranked by that value.

## Benchmark record

| Field | Value |
| --- | --- |
| Category | external |
| Measure | Share of tasks whose proof passes clean-room grading |
| Tasks | 56 Lean 4 formalization tasks |
| Difficulty | Research-level formal mathematics |
| Published by | [Autoform-Hard leaderboard and methodology](https://www.vals.ai/benchmarks/autoform_hard) |

Vals AI benchmark that asks agents to complete Lean 4 formalizations of graduate- and research-level mathematics, graded by a clean-room proof checker.

## Autoform-Hard ranking

No model in the catalog has a published Autoform-Hard score. The benchmark is defined by Autoform-Hard leaderboard and methodology, 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.
