# Walk and Climb Stairs Up (W.CS.U) on WOLF-VLA

Source: [Walk and Climb Stairs Up (W.CS.U) on WOLF-VLA](<https://www.sota2.com/research/sota/walk-and-climb-stairs-up-w-cs-u-on-wolf-vla>)

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

Data updated: 2026-06-25T06:51:44.169Z

Evaluation of agent performance on the Walk and Climb Stairs Up task using the WOLF-VLA dataset, measured by success rates and joint Range of Motion (ROM) errors.

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 | Walk and Climb Stairs Up (W.CS.U) |
| Dataset (including any stated split) | WOLF-VLA |
| Metric | Soft Success Rate |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 6 of 6 |
| 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

- [Soft Success Rate](<https://www.sota2.com/research/sota/walk-and-climb-stairs-up-w-cs-u-on-wolf-vla.md?metric=Soft%20Success%20Rate>): Higher is better; unit: PERCENT.

- [Standard Success Rate](<https://www.sota2.com/research/sota/walk-and-climb-stairs-up-w-cs-u-on-wolf-vla.md?metric=Standard%20Success%20Rate>): Higher is better; unit: PERCENT.

- [Hip ROM Error Rate (ΔHR)](<https://www.sota2.com/research/sota/walk-and-climb-stairs-up-w-cs-u-on-wolf-vla.md?metric=Hip%20ROM%20Error%20Rate%20(%CE%94HR)>): Lower is better; unit: PERCENT.

- [Knee ROM Error Rate (ΔKR)](<https://www.sota2.com/research/sota/walk-and-climb-stairs-up-w-cs-u-on-wolf-vla.md?metric=Knee%20ROM%20Error%20Rate%20(%CE%94KR)>): Lower is better; unit: PERCENT.

- [Ankle ROM Error Rate (ΔAR)](<https://www.sota2.com/research/sota/walk-and-climb-stairs-up-w-cs-u-on-wolf-vla.md?metric=Ankle%20ROM%20Error%20Rate%20(%CE%94AR)>): Lower is better; unit: PERCENT.

- [Average Success Rate](<https://www.sota2.com/research/sota/walk-and-climb-stairs-up-w-cs-u-on-wolf-vla.md?metric=Average%20Success%20Rate>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Soft Success Rate | Result date | Report paper |
| --- | --- | --- | --- |
| Groot-N1 | 63.3 | Not recorded | 6a3cb617206542251d7ca578 |
| Groot-N1 | 55 | Not recorded | 6a3cb617206542251d7ca578 |
| Groot-N1 | 50 | Not recorded | 6a3cb617206542251d7ca578 |
| Groot-N1 | 48.3 | Not recorded | 6a3cb617206542251d7ca578 |
| Groot-N1 | 48.3 | Not recorded | 6a3cb617206542251d7ca578 |
| Groot-N1 | 46.7 | Not recorded | 6a3cb617206542251d7ca578 |

### Groot-N1

Soft Success Rate: 63.3. Result ID: 6a3ccff4fbc373592c50eacd.

[Reporting paper](<https://www.sota2.com/research/paper/6a3cb617206542251d7ca578.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a3cb617206542251d7ca578.md>)

Recorded evaluation configuration: {"Horizon Length":"Medium","Disturbance Setting":"Dist."}. This record does not assert independent reproduction.

### Groot-N1

Soft Success Rate: 55. Result ID: 6a3ccff4fbc373592c50eaca.

[Reporting paper](<https://www.sota2.com/research/paper/6a3cb617206542251d7ca578.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a3cb617206542251d7ca578.md>)

Recorded evaluation configuration: {"Horizon Length":"Short","Disturbance Setting":"No Dist."}. This record does not assert independent reproduction.

### Groot-N1

Soft Success Rate: 50. Result ID: 6a3ccff4fbc373592c50eacf.

[Reporting paper](<https://www.sota2.com/research/paper/6a3cb617206542251d7ca578.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a3cb617206542251d7ca578.md>)

Recorded evaluation configuration: {"Horizon Length":"Long","Disturbance Setting":"Dist."}. This record does not assert independent reproduction.

### Groot-N1

Soft Success Rate: 48.3. Result ID: 6a3ccff4fbc373592c50eacc.

[Reporting paper](<https://www.sota2.com/research/paper/6a3cb617206542251d7ca578.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a3cb617206542251d7ca578.md>)

Recorded evaluation configuration: {"Horizon Length":"Medium","Disturbance Setting":"No Dist."}. This record does not assert independent reproduction.

### Groot-N1

Soft Success Rate: 48.3. Result ID: 6a3ccff4fbc373592c50eace.

[Reporting paper](<https://www.sota2.com/research/paper/6a3cb617206542251d7ca578.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a3cb617206542251d7ca578.md>)

Recorded evaluation configuration: {"Horizon Length":"Long","Disturbance Setting":"No Dist."}. This record does not assert independent reproduction.

### Groot-N1

Soft Success Rate: 46.7. Result ID: 6a3ccff4fbc373592c50eacb.

[Reporting paper](<https://www.sota2.com/research/paper/6a3cb617206542251d7ca578.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a3cb617206542251d7ca578.md>)

Recorded evaluation configuration: {"Horizon Length":"Short","Disturbance Setting":"Dist."}. This record does not assert independent reproduction.

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