# DocVQA 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-doc-vqa-provider-reports

Every model the catalog carries a published DocVQA value for, ranked by that value.

## Benchmark record

| Field | Value |
| --- | --- |
| Category | external |
| Measure | Text answers drawn from document images |
| Tasks | Questions about single document images; provider run counts undisclosed |
| Difficulty | — |
| Published by | [DocVQA: A Dataset for VQA on Document Images](https://www.docvqa.org/datasets/docvqa) |

DocVQA asks questions about a single document image. This page shows four historical Anthropic reports on the test split, with ANLS, zero-shot setup, report dates, and source cohorts kept visible.

## DocVQA ranking

No model in the catalog has a published DocVQA score. The benchmark is defined by DocVQA: A Dataset for VQA on Document Images, 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.