# Text-to-Image Metric Meta-Evaluation on TIFA (Original)

Source: [Text-to-Image Metric Meta-Evaluation on TIFA (Original)](<https://www.sota2.com/research/sota/text-to-image-metric-meta-evaluation-on-tifa-original>)

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

Data updated: 2026-04-21T10:45:48.397Z

Evaluation of Text-to-Image metrics using correlation analysis (Kendall/Pearson) on the original TIFA dataset.

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 | Text-to-Image Metric Meta-Evaluation |
| Dataset (including any stated split) | TIFA (Original) |
| Metric | Kendall Correlation |
| Unit | SCALAR |
| Direction | Higher 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

- [Kendall Correlation](<https://www.sota2.com/research/sota/text-to-image-metric-meta-evaluation-on-tifa-original.md?metric=Kendall%20Correlation>): Higher is better; unit: SCALAR.

- [Pearson Correlation](<https://www.sota2.com/research/sota/text-to-image-metric-meta-evaluation-on-tifa-original.md?metric=Pearson%20Correlation>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Kendall Correlation | Result date | Report paper |
| --- | --- | --- | --- |
| CROCScore | 0.55 | Not recorded | 68fa789f1e209131cea796a5 |
| CROCScore\_plain | 0.549 | Not recorded | 68fa789f1e209131cea796a5 |
| VQAScore | 0.532 | Not recorded | 68fa789f1e209131cea796a5 |
| Align | 0.299 | Not recorded | 68fa789f1e209131cea796a5 |
| BLIP2 | 0.294 | Not recorded | 68fa789f1e209131cea796a5 |

### CROCScore

Kendall Correlation: 0.55. Result ID: 69e754d647f34ce924ce5b1b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa789f1e209131cea796a5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa789f1e209131cea796a5.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### CROCScore\_plain

Kendall Correlation: 0.549. Result ID: 69e754d647f34ce924ce5b1a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa789f1e209131cea796a5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa789f1e209131cea796a5.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### VQAScore

Kendall Correlation: 0.532. Result ID: 69e754d647f34ce924ce5b19.

[Reporting paper](<https://www.sota2.com/research/paper/68fa789f1e209131cea796a5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73a81e209131cea5dbb3.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### Align

Kendall Correlation: 0.299. Result ID: 69e754d647f34ce924ce5b17.

[Reporting paper](<https://www.sota2.com/research/paper/68fa789f1e209131cea796a5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a201e209131cea261e7.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### BLIP2

Kendall Correlation: 0.294. Result ID: 69e754d647f34ce924ce5b18.

[Reporting paper](<https://www.sota2.com/research/paper/68fa789f1e209131cea796a5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6fb71e209131cea46fe6.md>)

[Implementation](<https://github.com/salesforce/LAVIS/tree/main/projects/blip2>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

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