# Long-horizon Robotic Instruction Following on Libero long

Source: [Long-horizon Robotic Instruction Following on Libero long](<https://www.sota2.com/research/sota/long-horizon-robotic-instruction-following-on-libero-long>)

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

Data updated: 2026-05-12T12:31:54.951Z

Evaluation of long-horizon robotic instruction following performance on the Libero long dataset, reporting success rates for individual, complex manipulation instructions.

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 | Long-horizon robotic instruction following |
| Dataset (including any stated split) | Libero long |
| Metric | Soup and Sauce in Basket Success Rate |
| 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

- [Soup and Sauce in Basket Success Rate](<https://www.sota2.com/research/sota/long-horizon-robotic-instruction-following-on-libero-long.md?metric=Soup%20and%20Sauce%20in%20Basket%20Success%20Rate>): Higher is better; unit: PERCENT.

- [Cheese and Butter in Basket Success Rate](<https://www.sota2.com/research/sota/long-horizon-robotic-instruction-following-on-libero-long.md?metric=Cheese%20and%20Butter%20in%20Basket%20Success%20Rate>): Higher is better; unit: PERCENT.

- [Turn on Stove and Place Moka Success Rate](<https://www.sota2.com/research/sota/long-horizon-robotic-instruction-following-on-libero-long.md?metric=Turn%20on%20Stove%20and%20Place%20Moka%20Success%20Rate>): Higher is better; unit: PERCENT.

- [Black Bowl in Drawer Success Rate](<https://www.sota2.com/research/sota/long-horizon-robotic-instruction-following-on-libero-long.md?metric=Black%20Bowl%20in%20Drawer%20Success%20Rate>): Higher is better; unit: PERCENT.

- [Mugs on Plates Success Rate](<https://www.sota2.com/research/sota/long-horizon-robotic-instruction-following-on-libero-long.md?metric=Mugs%20on%20Plates%20Success%20Rate>): Higher is better; unit: PERCENT.

- [Book in Caddy Success Rate](<https://www.sota2.com/research/sota/long-horizon-robotic-instruction-following-on-libero-long.md?metric=Book%20in%20Caddy%20Success%20Rate>): Higher is better; unit: PERCENT.

- [Mug and Pudding on Plate Success Rate](<https://www.sota2.com/research/sota/long-horizon-robotic-instruction-following-on-libero-long.md?metric=Mug%20and%20Pudding%20on%20Plate%20Success%20Rate>): Higher is better; unit: PERCENT.

- [Soup and Cheese in Basket Success Rate](<https://www.sota2.com/research/sota/long-horizon-robotic-instruction-following-on-libero-long.md?metric=Soup%20and%20Cheese%20in%20Basket%20Success%20Rate>): Higher is better; unit: PERCENT.

- [Moka Pots on Stove Success Rate](<https://www.sota2.com/research/sota/long-horizon-robotic-instruction-following-on-libero-long.md?metric=Moka%20Pots%20on%20Stove%20Success%20Rate>): Higher is better; unit: PERCENT.

- [Mug in Microwave Success Rate](<https://www.sota2.com/research/sota/long-horizon-robotic-instruction-following-on-libero-long.md?metric=Mug%20in%20Microwave%20Success%20Rate>): Higher is better; unit: PERCENT.

- [Average Success Rate](<https://www.sota2.com/research/sota/long-horizon-robotic-instruction-following-on-libero-long.md?metric=Average%20Success%20Rate>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Soup and Sauce in Basket Success Rate | Result date | Report paper |
| --- | --- | --- | --- |
| π0.5 + TACO | 100 | Not recorded | 6a02b46ddbc836b87d824b7f |
| CAPS | 100 | Not recorded | 6a02b46ddbc836b87d824b7f |
| π0.5 | 98 | Not recorded | 6a02b46ddbc836b87d824b7f |
| Robomonkey\* | 59 | Not recorded | 6a02b46ddbc836b87d824b7f |
| OpenVLA\* | 36 | Not recorded | 6a02b46ddbc836b87d824b7f |

### π0.5 + TACO

Soup and Sauce in Basket Success Rate: 100. Result ID: 6a031c5747f34ce924e74636.

[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: {"action sampling temperature":"1"}. This record does not assert independent reproduction.

### CAPS

Soup and Sauce in Basket Success Rate: 100. Result ID: 6a031c5747f34ce924e74637.

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

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

Recorded evaluation configuration: {"action sampling temperature":"1","base policy":"π0.5"}. This record does not assert independent reproduction.

### π0.5

Soup and Sauce in Basket Success Rate: 98. Result ID: 6a031c5747f34ce924e74635.

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

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

Recorded evaluation configuration: {"action sampling temperature":"1"}. This record does not assert independent reproduction.

### Robomonkey\*

Soup and Sauce in Basket Success Rate: 59. Result ID: 6a031c5747f34ce924e74639.

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

[Method origin paper](<https://www.sota2.com/research/paper/68fa79da1e209131cea7fc19.md>)

Recorded evaluation configuration: {"action sampling temperature":"1"}. This record does not assert independent reproduction.

### OpenVLA\*

Soup and Sauce in Basket Success Rate: 36. Result ID: 6a031c5747f34ce924e74638.

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

[Method origin paper](<https://www.sota2.com/research/paper/68fa74c31e209131cea63a36.md>)

[Implementation](<https://openvla.github.io/>)

Recorded evaluation configuration: {"action sampling temperature":"1"}. This record does not assert independent reproduction.

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