# Box Refill on Real-world Manipulation Tasks

Source: [Box Refill on Real-world Manipulation Tasks](<https://www.sota2.com/research/sota/box-refill-on-real-world-manipulation-tasks>)

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

Data updated: 2026-06-23T12:51:18.118Z

Evaluation of model performance on the Box Refill task using the Real-world Manipulation Tasks dataset, measured by TSR and SCR.

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 | Box Refill |
| Dataset (including any stated split) | Real-world Manipulation Tasks |
| Metric | TSR |
| Unit | SCALAR |
| 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

- [TSR](<https://www.sota2.com/research/sota/box-refill-on-real-world-manipulation-tasks.md?metric=TSR>): Higher is better; unit: SCALAR.

- [SCR](<https://www.sota2.com/research/sota/box-refill-on-real-world-manipulation-tasks.md?metric=SCR>): Higher is better; unit: SCALAR.

## Recorded results

| Method | TSR | Result date | Report paper |
| --- | --- | --- | --- |
| KEMO | 7 | Not recorded | 6a3a13bf206542251d7c7933 |
| π0.5 | 4 | Not recorded | 6a3a13bf206542251d7c7933 |
| MemoryVLA | 0 | Not recorded | 6a3a13bf206542251d7c7933 |

### KEMO

TSR: 7. Result ID: 6a3a8145fbc373592c394276.

[Reporting paper](<https://www.sota2.com/research/paper/6a3a13bf206542251d7c7933.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a3a13bf206542251d7c7933.md>)

Recorded evaluation configuration: {"type":"memory-augmented"}. This record does not assert independent reproduction.

### π0.5

TSR: 4. Result ID: 6a3a8145fbc373592c394274.

[Reporting paper](<https://www.sota2.com/research/paper/6a3a13bf206542251d7c7933.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa783a1e209131cea774f1.md>)

Recorded evaluation configuration: {"type":"memory-free"}. This record does not assert independent reproduction.

### MemoryVLA

TSR: 0. Result ID: 6a3a8145fbc373592c394275.

[Reporting paper](<https://www.sota2.com/research/paper/6a3a13bf206542251d7c7933.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7adc1e209131cea858c5.md>)

Recorded evaluation configuration: {"type":"memory-augmented"}. This record does not assert independent reproduction.

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