# Multimodal Open-ended Utility Evaluation on MM-Vet v1 (test)

Source: [Multimodal Open-ended Utility Evaluation on MM-Vet v1 (test)](<https://www.sota2.com/research/sota/multimodal-open-ended-utility-evaluation-on-mm-vet-v1-test>)

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

Data updated: 2026-04-13T08:09:45.973Z

Evaluation of model performance on the test split of MM-Vet version 1, focusing on open-ended multimodal utility, measured by the Utility Score.

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 Utility Evaluation |
| Dataset (including any stated split) | MM-Vet v1 (test) |
| Metric | Utility Score |
| Unit | PERCENT |
| 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

- [Utility Score](<https://www.sota2.com/research/sota/multimodal-open-ended-utility-evaluation-on-mm-vet-v1-test.md?metric=Utility%20Score>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Utility Score | Result date | Report paper |
| --- | --- | --- | --- |
| No Steering | 68.1 | Not recorded | 69dc78987d0172140ec78ba3 |
| DACO | 65 | Not recorded | 69dc78987d0172140ec78ba3 |
| Prompting | 64.2 | Not recorded | 69dc78987d0172140ec78ba3 |
| MOP | 62.8 | Not recorded | 69dc78987d0172140ec78ba3 |
| ActAdd | 60.9 | Not recorded | 69dc78987d0172140ec78ba3 |

### No Steering

Utility Score: 68.1. Result ID: 69dca36d47f34ce924c3716a.

[Reporting paper](<https://www.sota2.com/research/paper/69dc78987d0172140ec78ba3.md>)

Recorded evaluation configuration: {"Steering Method":"None"}. This record does not assert independent reproduction.

### DACO

Utility Score: 65. Result ID: 69dca36d47f34ce924c3716e.

[Reporting paper](<https://www.sota2.com/research/paper/69dc78987d0172140ec78ba3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69dc78987d0172140ec78ba3.md>)

Recorded evaluation configuration: {"Steering Method":"DACO"}. This record does not assert independent reproduction.

### Prompting

Utility Score: 64.2. Result ID: 69dca36d47f34ce924c3716b.

[Reporting paper](<https://www.sota2.com/research/paper/69dc78987d0172140ec78ba3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73c11e209131cea5e455.md>)

Recorded evaluation configuration: {"Steering Method":"Prompting"}. This record does not assert independent reproduction.

### MOP

Utility Score: 62.8. Result ID: 69dca36d47f34ce924c3716d.

[Reporting paper](<https://www.sota2.com/research/paper/69dc78987d0172140ec78ba3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75881e209131cea686ad.md>)

[Implementation](<https://github.com/peterljq/Parsimonious-Concept-Engineering>)

Recorded evaluation configuration: {"Steering Method":"MOP"}. This record does not assert independent reproduction.

### ActAdd

Utility Score: 60.9. Result ID: 69dca36d47f34ce924c3716c.

[Reporting paper](<https://www.sota2.com/research/paper/69dc78987d0172140ec78ba3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa754e1e209131cea66fd9.md>)

Recorded evaluation configuration: {"Steering Method":"Activation Addition"}. This record does not assert independent reproduction.

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