# Visual Question Answering on TextVQA (ANLS, Token, FTL)

Source: [Visual Question Answering on TextVQA (ANLS, Token, FTL)](<https://www.sota2.com/research/sota/visual-question-answering-on-textvqa-anls-token-ftl>)

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

Data updated: 2026-02-26T05:45:01.994Z

Evaluation of model performance on the TextVQA dataset for Visual Question Answering, utilizing ANLS, Token count, and Forward Time Latency (FTL) as primary metrics.

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 | Visual Question Answering |
| Dataset (including any stated split) | TextVQA |
| Metric | FTL (s) |
| Unit | TIME |
| Direction | Lower is better |
| Results loaded | 5 of 5 |
| 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

- [FTL (s)](<https://www.sota2.com/research/sota/visual-question-answering-on-textvqa-anls-token-ftl.md?metric=FTL%20(s)>): Lower is better; unit: TIME.

- [Token Count](<https://www.sota2.com/research/sota/visual-question-answering-on-textvqa-anls-token-ftl.md?metric=Token%20Count>): Higher is better; unit: SCALAR.

- [ANLS](<https://www.sota2.com/research/sota/visual-question-answering-on-textvqa-anls-token-ftl.md?metric=ANLS>): Higher is better; unit: PERCENT.

## Recorded results

| Method | FTL (s) | Result date | Report paper |
| --- | --- | --- | --- |
| DocOwl2 | 0.23 | Not recorded | 68fa74bb1e209131cea635b7 |
| TextMonkey | 0.5 | Not recorded | 68fa74bb1e209131cea635b7 |
| DocOwl 1.5 | 0.56 | Not recorded | 68fa74bb1e209131cea635b7 |
| InternVL 2 | 1.01 | Not recorded | 68fa74bb1e209131cea635b7 |
| IXC 2.5 | 1.11 | Not recorded | 68fa74bb1e209131cea635b7 |

### DocOwl2

FTL (s): 0.23. Result ID: 6993562c3a6c314849154266.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74bb1e209131cea635b7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74bb1e209131cea635b7.md>)

[Implementation](<https://github.com/X-PLUG/mPLUG-DocOwl/tree/main/DocOwl2>)

Recorded evaluation configuration: {"Size":"8B"}. This record does not assert independent reproduction.

### TextMonkey

FTL (s): 0.5. Result ID: 6993562c3a6c314849154265.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74bb1e209131cea635b7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa727f1e209131cea56c52.md>)

Recorded evaluation configuration: {"Size":"9B"}. This record does not assert independent reproduction.

### DocOwl 1.5

FTL (s): 0.56. Result ID: 6993562c3a6c314849154264.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74bb1e209131cea635b7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72901e209131cea571df.md>)

Recorded evaluation configuration: {"Size":"8B"}. This record does not assert independent reproduction.

### InternVL 2

FTL (s): 1.01. Result ID: 6993562c3a6c314849154262.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74bb1e209131cea635b7.md>)

Recorded evaluation configuration: {"Size":"8B"}. This record does not assert independent reproduction.

### IXC 2.5

FTL (s): 1.11. Result ID: 6993562c3a6c314849154263.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74bb1e209131cea635b7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72d01e209131cea58ace.md>)

[Implementation](<https://github.com/InternLM/InternLM-XComposer>)

Recorded evaluation configuration: {"Size":"7B"}. This record does not assert independent reproduction.

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