# Robot Task Completion on VLA-arena Level-1 (episodes 15-49)

Source: [Robot Task Completion on VLA-arena Level-1 (episodes 15-49)](<https://www.sota2.com/research/sota/robot-task-completion-on-vla-arena-level-1-episodes-15-49>)

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

Data updated: 2026-05-13T10:38:19.686Z

Evaluation of robot task completion performance on the VLA-arena Level-1 subset (episodes 15-49), measuring success rates and wall-clock time across specific conditions (Extrapolation, Distribution, Safety, Long Horizon).

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 | Robot Task Completion |
| Dataset (including any stated split) | VLA-arena Level-1 (episodes 15-49) |
| Metric | Success Rate (Extr.) |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 3 of 3 |
| 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

- [Success Rate (Extr.)](<https://www.sota2.com/research/sota/robot-task-completion-on-vla-arena-level-1-episodes-15-49.md?metric=Success%20Rate%20(Extr.)>): Higher is better; unit: PERCENT.

- [Success Rate (Distr.)](<https://www.sota2.com/research/sota/robot-task-completion-on-vla-arena-level-1-episodes-15-49.md?metric=Success%20Rate%20(Distr.)>): Higher is better; unit: PERCENT.

- [Success Rate (Safe)](<https://www.sota2.com/research/sota/robot-task-completion-on-vla-arena-level-1-episodes-15-49.md?metric=Success%20Rate%20(Safe)>): Higher is better; unit: PERCENT.

- [Success Rate (LongH)](<https://www.sota2.com/research/sota/robot-task-completion-on-vla-arena-level-1-episodes-15-49.md?metric=Success%20Rate%20(LongH)>): Higher is better; unit: PERCENT.

- [Success Rate (Mean)](<https://www.sota2.com/research/sota/robot-task-completion-on-vla-arena-level-1-episodes-15-49.md?metric=Success%20Rate%20(Mean)>): Higher is better; unit: PERCENT.

- [Wall-Clock Time (All) (Extr.)](<https://www.sota2.com/research/sota/robot-task-completion-on-vla-arena-level-1-episodes-15-49.md?metric=Wall-Clock%20Time%20(All)%20(Extr.)>): Lower is better; unit: TIME.

- [Wall-Clock Time (All) (Distr.)](<https://www.sota2.com/research/sota/robot-task-completion-on-vla-arena-level-1-episodes-15-49.md?metric=Wall-Clock%20Time%20(All)%20(Distr.)>): Lower is better; unit: TIME.

- [Wall-Clock Time (All) (Safe)](<https://www.sota2.com/research/sota/robot-task-completion-on-vla-arena-level-1-episodes-15-49.md?metric=Wall-Clock%20Time%20(All)%20(Safe)>): Lower is better; unit: TIME.

- [Wall-Clock Time (All) (LongH)](<https://www.sota2.com/research/sota/robot-task-completion-on-vla-arena-level-1-episodes-15-49.md?metric=Wall-Clock%20Time%20(All)%20(LongH)>): Lower is better; unit: TIME.

- [Wall-Clock Time (All) (Mean)](<https://www.sota2.com/research/sota/robot-task-completion-on-vla-arena-level-1-episodes-15-49.md?metric=Wall-Clock%20Time%20(All)%20(Mean)>): Lower is better; unit: TIME.

- [Wall-Clock Time (Succ.) (Extr.)](<https://www.sota2.com/research/sota/robot-task-completion-on-vla-arena-level-1-episodes-15-49.md?metric=Wall-Clock%20Time%20(Succ.)%20(Extr.)>): Lower is better; unit: TIME.

- [Wall-Clock Time (Succ.) (Distr.)](<https://www.sota2.com/research/sota/robot-task-completion-on-vla-arena-level-1-episodes-15-49.md?metric=Wall-Clock%20Time%20(Succ.)%20(Distr.)>): Lower is better; unit: TIME.

- [Wall-Clock Time (Succ.) (Safe)](<https://www.sota2.com/research/sota/robot-task-completion-on-vla-arena-level-1-episodes-15-49.md?metric=Wall-Clock%20Time%20(Succ.)%20(Safe)>): Lower is better; unit: TIME.

- [Wall-Clock Time (Succ.) (LongH)](<https://www.sota2.com/research/sota/robot-task-completion-on-vla-arena-level-1-episodes-15-49.md?metric=Wall-Clock%20Time%20(Succ.)%20(LongH)>): Lower is better; unit: TIME.

- [Wall-Clock Time (Succ.) (Mean)](<https://www.sota2.com/research/sota/robot-task-completion-on-vla-arena-level-1-episodes-15-49.md?metric=Wall-Clock%20Time%20(Succ.)%20(Mean)>): Lower is better; unit: TIME.

## Recorded results

| Method | Success Rate (Extr.) | Result date | Report paper |
| --- | --- | --- | --- |
| Premover | 25.9 | Not recorded | 6a0405dadbc836b87d827870 |
| Full-prompt | 25.1 | Not recorded | 6a0405dadbc836b87d827870 |
| Naive Premoving | 8.6 | Not recorded | 6a0405dadbc836b87d827870 |

### Premover

Success Rate (Extr.): 25.9. Result ID: 6a04548247f34ce924eae93a.

[Reporting paper](<https://www.sota2.com/research/paper/6a0405dadbc836b87d827870.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a0405dadbc836b87d827870.md>)

Recorded evaluation configuration: {"Setting":"Premover (ours)","Policy":"π0.5"}. This record does not assert independent reproduction.

### Full-prompt

Success Rate (Extr.): 25.1. Result ID: 6a04548247f34ce924eae938.

[Reporting paper](<https://www.sota2.com/research/paper/6a0405dadbc836b87d827870.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70e61e209131cea4dc9e.md>)

[Implementation](<https://libero-project.github.io/>)

Recorded evaluation configuration: {"Setting":"Full-prompt","Policy":"π0.5"}. This record does not assert independent reproduction.

### Naive Premoving

Success Rate (Extr.): 8.6. Result ID: 6a04548247f34ce924eae939.

[Reporting paper](<https://www.sota2.com/research/paper/6a0405dadbc836b87d827870.md>)

Recorded evaluation configuration: {"Setting":"Naive Premoving","Policy":"π0.5"}. This record does not assert independent reproduction.

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