# Visual Question Answering on TextVQA (Performance and Bit Metrics)

Source: [Visual Question Answering on TextVQA (Performance and Bit Metrics)](<https://www.sota2.com/research/sota/visual-question-answering-on-textvqa-performance-and-bit-metrics>)

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

Data updated: 2026-02-26T05:37:41.158Z

Evaluation of model performance on the TextVQA dataset for Visual Question Answering, focusing on Baseline Performance, Final Performance, and Critical Bits 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 | Baseline Performance |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 1 of 1 |
| 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

- [Baseline Performance](<https://www.sota2.com/research/sota/visual-question-answering-on-textvqa-performance-and-bit-metrics.md?metric=Baseline%20Performance>): Higher is better; unit: PERCENT.

- [Final Performance](<https://www.sota2.com/research/sota/visual-question-answering-on-textvqa-performance-and-bit-metrics.md?metric=Final%20Performance>): Higher is better; unit: PERCENT.

- [Critical Bits](<https://www.sota2.com/research/sota/visual-question-answering-on-textvqa-performance-and-bit-metrics.md?metric=Critical%20Bits>): Lower is better; unit: SCALAR.

## Recorded results

| Method | Baseline Performance | Result date | Report paper |
| --- | --- | --- | --- |
| FlipLLM | 62.5 | Not recorded | 693a502f6cfd488761a54c2d |

### FlipLLM

Baseline Performance: 62.5. Result ID: 699704475698665ec45169a6.

[Reporting paper](<https://www.sota2.com/research/paper/693a502f6cfd488761a54c2d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/693a502f6cfd488761a54c2d.md>)

Recorded evaluation configuration: {"Type":"VLM","Target Model":"LLaVA 1.6","Parameters":"7B"}. This record does not assert independent reproduction.

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