# Multimodal Open-ended Evaluation on WildVision (test)

Source: [Multimodal Open-ended Evaluation on WildVision (test)](<https://www.sota2.com/research/sota/multimodal-open-ended-evaluation-on-wildvision-test>)

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

Data updated: 2026-03-05T08:38:20.478Z

Evaluation of model performance on open-ended multimodal tasks using the test split of the WildVision 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 | Multimodal Open-ended Evaluation |
| Dataset (including any stated split) | WildVision (test) |
| Metric | Latxa Win % |
| Unit | PERCENT |
| 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

- [Latxa Win %](<https://www.sota2.com/research/sota/multimodal-open-ended-evaluation-on-wildvision-test.md?metric=Latxa%20Win%20%25>): Higher is better; unit: PERCENT.

- [Tie %](<https://www.sota2.com/research/sota/multimodal-open-ended-evaluation-on-wildvision-test.md?metric=Tie%20%25>): Higher is better; unit: PERCENT.

- [Llama Win %](<https://www.sota2.com/research/sota/multimodal-open-ended-evaluation-on-wildvision-test.md?metric=Llama%20Win%20%25>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Latxa Win % | Result date | Report paper |
| --- | --- | --- | --- |
| Open-ended MLLM Comparison | 31.44 | Not recorded | 691566220052cac1dc65d972 |
| Open-ended MLLM Comparison | 23.11 | Not recorded | 691566220052cac1dc65d972 |

### Open-ended MLLM Comparison

Latxa Win %: 31.44. Result ID: 69a940e96dbb7075b952bc2a.

[Reporting paper](<https://www.sota2.com/research/paper/691566220052cac1dc65d972.md>)

[Method origin paper](<https://www.sota2.com/research/paper/691566220052cac1dc65d972.md>)

Recorded evaluation configuration: {"Evaluation Paradigm":"GPT-5"}. This record does not assert independent reproduction.

### Open-ended MLLM Comparison

Latxa Win %: 23.11. Result ID: 69a940e96dbb7075b952bc29.

[Reporting paper](<https://www.sota2.com/research/paper/691566220052cac1dc65d972.md>)

[Method origin paper](<https://www.sota2.com/research/paper/691566220052cac1dc65d972.md>)

Recorded evaluation configuration: {"Evaluation Paradigm":"Human"}. This record does not assert independent reproduction.

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