# Document Question Answering on D1

Source: [Document Question Answering on D1](<https://www.sota2.com/research/sota/document-question-answering-on-d1>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-02-26T05:39:52.579Z

Evaluation of model performance on the D1 dataset for Document Question Answering.

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

| Scope | Recorded value |
| --- | --- |
| Task | Document Question Answering |
| Dataset (including any stated split) | D1 |
| Metric | Correct Answers |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 2 of 2 |
| Coverage | All results currently returned for this benchmark |

Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol.

## Metrics

- [Correct Answers](<https://www.sota2.com/research/sota/document-question-answering-on-d1.md?metric=Correct%20Answers>): Higher is better; unit: SCALAR.

- [Partial Answers](<https://www.sota2.com/research/sota/document-question-answering-on-d1.md?metric=Partial%20Answers>): Higher is better; unit: SCALAR.

- [Effective Accuracy](<https://www.sota2.com/research/sota/document-question-answering-on-d1.md?metric=Effective%20Accuracy>): Higher is better; unit: PERCENT.

- [Ingestion VLM Tokens](<https://www.sota2.com/research/sota/document-question-answering-on-d1.md?metric=Ingestion%20VLM%20Tokens>): Lower is better; unit: SCALAR.

- [Inference VLM Tokens](<https://www.sota2.com/research/sota/document-question-answering-on-d1.md?metric=Inference%20VLM%20Tokens>): Lower is better; unit: SCALAR.

## Recorded results

| Method | Correct Answers | Result date | Report paper |
| --- | --- | --- | --- |
| Pre-ingest | 20 | Not recorded | 6993f68e9ebc499c97409ed6 |
| DVI | 17 | Not recorded | 6993f68e9ebc499c97409ed6 |

### Pre-ingest

Correct Answers: 20. Result ID: 699a92cb5698665ec41da3c1.

[Reporting paper](<https://www.sota2.com/research/paper/6993f68e9ebc499c97409ed6.md>)

Recorded evaluation configuration: {"Description type":"Blind descriptions"}. This record does not assert independent reproduction.

### DVI

Correct Answers: 17. Result ID: 699a92cb5698665ec41da3c2.

[Reporting paper](<https://www.sota2.com/research/paper/6993f68e9ebc499c97409ed6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6993f68e9ebc499c97409ed6.md>)

Recorded evaluation configuration: {"Description type":"On-demand examination","Ingestion type":"Rule-based/Heuristic"}. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.