# Robot Manipulation on Real-World Benchmark 10 Tasks

Source: [Robot Manipulation on Real-World Benchmark 10 Tasks](<https://www.sota2.com/research/sota/robot-manipulation-on-real-world-benchmark-10-tasks>)

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

Data updated: 2026-05-12T12:26:28.352Z

Evaluation of robot manipulation capabilities across 10 specific real-world tasks, focusing on sequential, coordination, and precision success rates.

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 Manipulation |
| Dataset (including any stated split) | Real-World Benchmark 10 Tasks |
| Metric | Sequential Success Rate |
| 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

- [Sequential Success Rate](<https://www.sota2.com/research/sota/robot-manipulation-on-real-world-benchmark-10-tasks.md?metric=Sequential%20Success%20Rate>): Higher is better; unit: PERCENT.

- [Coordination Success Rate](<https://www.sota2.com/research/sota/robot-manipulation-on-real-world-benchmark-10-tasks.md?metric=Coordination%20Success%20Rate>): Higher is better; unit: PERCENT.

- [Precision Success Rate](<https://www.sota2.com/research/sota/robot-manipulation-on-real-world-benchmark-10-tasks.md?metric=Precision%20Success%20Rate>): Higher is better; unit: PERCENT.

- [Overall Success Rate (Weighted)](<https://www.sota2.com/research/sota/robot-manipulation-on-real-world-benchmark-10-tasks.md?metric=Overall%20Success%20Rate%20(Weighted)>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Sequential Success Rate | Result date | Report paper |
| --- | --- | --- | --- |
| CAPS | 75 | Not recorded | 6a02b46ddbc836b87d824b7f |
| TACO | 55 | Not recorded | 6a02b46ddbc836b87d824b7f |
| Base | 40 | Not recorded | 6a02b46ddbc836b87d824b7f |

### CAPS

Sequential Success Rate: 75. Result ID: 6a031c5747f34ce924e74630.

[Reporting paper](<https://www.sota2.com/research/paper/6a02b46ddbc836b87d824b7f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a02b46ddbc836b87d824b7f.md>)

Recorded evaluation configuration: {"variant":"Full Model (Adaptive)"}. This record does not assert independent reproduction.

### TACO

Sequential Success Rate: 55. Result ID: 6a031c5747f34ce924e7462f.

[Reporting paper](<https://www.sota2.com/research/paper/6a02b46ddbc836b87d824b7f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/692fc42bd6b0dd334293340b.md>)

[Implementation](<https://github.com/breez3young/TACO>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### Base

Sequential Success Rate: 40. Result ID: 6a031c5747f34ce924e7462e.

[Reporting paper](<https://www.sota2.com/research/paper/6a02b46ddbc836b87d824b7f.md>)

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

Recorded evaluation configuration: {"description":"Base Policy (π0.5)"}. This record does not assert independent reproduction.

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