# Physical Red Teaming on RedVLA Conditional-Level Scenarios

Source: [Physical Red Teaming on RedVLA Conditional-Level Scenarios](<https://www.sota2.com/research/sota/physical-red-teaming-on-redvla-conditional-level-scenarios>)

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

Data updated: 2026-04-27T07:39:51.188Z

Evaluation of model performance in physical red teaming scenarios using the RedVLA Conditional-Level Scenarios dataset, measured by Attack Success Rate (ASR) and Success Rate (SR).

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 | Physical Red Teaming |
| Dataset (including any stated split) | RedVLA Conditional-Level Scenarios |
| Metric | ASR |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 24 of 24 |
| 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

- [ASR](<https://www.sota2.com/research/sota/physical-red-teaming-on-redvla-conditional-level-scenarios.md?metric=ASR>): Higher is better; unit: PERCENT.

- [SR](<https://www.sota2.com/research/sota/physical-red-teaming-on-redvla-conditional-level-scenarios.md?metric=SR>): Higher is better; unit: PERCENT.

## Recorded results

| Method | ASR | Result date | Report paper |
| --- | --- | --- | --- |
| π0.5 | 98 | Not recorded | 69eeed6a55a3c32af89f9657 |
| π0.5 | 96.7 | Not recorded | 69eeed6a55a3c32af89f9657 |
| OpenVLA-OFT | 96.7 | Not recorded | 69eeed6a55a3c32af89f9657 |
| π0 | 96.7 | Not recorded | 69eeed6a55a3c32af89f9657 |
| VLA-Adapter-Pro | 94 | Not recorded | 69eeed6a55a3c32af89f9657 |
| OpenVLA-OFT | 93.3 | Not recorded | 69eeed6a55a3c32af89f9657 |
| VLA-Adapter-Pro | 93.3 | Not recorded | 69eeed6a55a3c32af89f9657 |
| π0 | 93.3 | Not recorded | 69eeed6a55a3c32af89f9657 |
| OpenVLA-OFT | 92 | Not recorded | 69eeed6a55a3c32af89f9657 |
| π0.5 | 90 | Not recorded | 69eeed6a55a3c32af89f9657 |
| π0.5 | 90 | Not recorded | 69eeed6a55a3c32af89f9657 |
| VLA-Adapter | 90 | Not recorded | 69eeed6a55a3c32af89f9657 |
| VLA-Adapter | 86.7 | Not recorded | 69eeed6a55a3c32af89f9657 |
| VLA-Adapter-Pro | 83.3 | Not recorded | 69eeed6a55a3c32af89f9657 |
| VLA-Adapter | 80 | Not recorded | 69eeed6a55a3c32af89f9657 |
| π0 | 80 | Not recorded | 69eeed6a55a3c32af89f9657 |
| π0 | 78 | Not recorded | 69eeed6a55a3c32af89f9657 |
| OpenVLA-OFT | 73.3 | Not recorded | 69eeed6a55a3c32af89f9657 |
| VLA-Adapter-Pro | 73.3 | Not recorded | 69eeed6a55a3c32af89f9657 |
| VLA-Adapter | 70 | Not recorded | 69eeed6a55a3c32af89f9657 |
| OpenVLA | 28 | Not recorded | 69eeed6a55a3c32af89f9657 |
| OpenVLA | 26.7 | Not recorded | 69eeed6a55a3c32af89f9657 |
| OpenVLA | 26.7 | Not recorded | 69eeed6a55a3c32af89f9657 |
| OpenVLA | 23.3 | Not recorded | 69eeed6a55a3c32af89f9657 |

### π0.5

ASR: 98. Result ID: 69ef115947f34ce924d4ef63.

[Reporting paper](<https://www.sota2.com/research/paper/69eeed6a55a3c32af89f9657.md>)

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

Recorded evaluation configuration: {"Scenario":"Environmental Harm"}. This record does not assert independent reproduction.

### π0.5

ASR: 96.7. Result ID: 69ef115947f34ce924d4ef51.

[Reporting paper](<https://www.sota2.com/research/paper/69eeed6a55a3c32af89f9657.md>)

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

Recorded evaluation configuration: {"Scenario":"Resource Damage (skull-marked)"}. This record does not assert independent reproduction.

### OpenVLA-OFT

ASR: 96.7. Result ID: 69ef115947f34ce924d4ef59.

[Reporting paper](<https://www.sota2.com/research/paper/69eeed6a55a3c32af89f9657.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78471e209131cea7794b.md>)

Recorded evaluation configuration: {"Scenario":"Robot Damage"}. This record does not assert independent reproduction.

### π0

ASR: 96.7. Result ID: 69ef115947f34ce924d4ef5c.

[Reporting paper](<https://www.sota2.com/research/paper/69eeed6a55a3c32af89f9657.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75aa1e209131cea6929a.md>)

Recorded evaluation configuration: {"Scenario":"Robot Damage"}. This record does not assert independent reproduction.

### VLA-Adapter-Pro

ASR: 94. Result ID: 69ef115947f34ce924d4ef61.

[Reporting paper](<https://www.sota2.com/research/paper/69eeed6a55a3c32af89f9657.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7b861e209131cea88e51.md>)

Recorded evaluation configuration: {"Scenario":"Environmental Harm"}. This record does not assert independent reproduction.

### OpenVLA-OFT

ASR: 93.3. Result ID: 69ef115947f34ce924d4ef4d.

[Reporting paper](<https://www.sota2.com/research/paper/69eeed6a55a3c32af89f9657.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78471e209131cea7794b.md>)

Recorded evaluation configuration: {"Scenario":"Resource Damage (skull-marked)"}. This record does not assert independent reproduction.

### VLA-Adapter-Pro

ASR: 93.3. Result ID: 69ef115947f34ce924d4ef4f.

[Reporting paper](<https://www.sota2.com/research/paper/69eeed6a55a3c32af89f9657.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7b861e209131cea88e51.md>)

Recorded evaluation configuration: {"Scenario":"Resource Damage (skull-marked)"}. This record does not assert independent reproduction.

### π0

ASR: 93.3. Result ID: 69ef115947f34ce924d4ef50.

[Reporting paper](<https://www.sota2.com/research/paper/69eeed6a55a3c32af89f9657.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75aa1e209131cea6929a.md>)

Recorded evaluation configuration: {"Scenario":"Resource Damage (skull-marked)"}. This record does not assert independent reproduction.

### OpenVLA-OFT

ASR: 92. Result ID: 69ef115947f34ce924d4ef5f.

[Reporting paper](<https://www.sota2.com/research/paper/69eeed6a55a3c32af89f9657.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78471e209131cea7794b.md>)

Recorded evaluation configuration: {"Scenario":"Environmental Harm"}. This record does not assert independent reproduction.

### π0.5

ASR: 90. Result ID: 69ef115947f34ce924d4ef57.

[Reporting paper](<https://www.sota2.com/research/paper/69eeed6a55a3c32af89f9657.md>)

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

Recorded evaluation configuration: {"Scenario":"Dangerous Item Misuse"}. This record does not assert independent reproduction.

### π0.5

ASR: 90. Result ID: 69ef115947f34ce924d4ef5d.

[Reporting paper](<https://www.sota2.com/research/paper/69eeed6a55a3c32af89f9657.md>)

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

Recorded evaluation configuration: {"Scenario":"Robot Damage"}. This record does not assert independent reproduction.

### VLA-Adapter

ASR: 90. Result ID: 69ef115947f34ce924d4ef60.

[Reporting paper](<https://www.sota2.com/research/paper/69eeed6a55a3c32af89f9657.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7b861e209131cea88e51.md>)

Recorded evaluation configuration: {"Scenario":"Environmental Harm"}. This record does not assert independent reproduction.

### VLA-Adapter

ASR: 86.7. Result ID: 69ef115947f34ce924d4ef5a.

[Reporting paper](<https://www.sota2.com/research/paper/69eeed6a55a3c32af89f9657.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7b861e209131cea88e51.md>)

Recorded evaluation configuration: {"Scenario":"Robot Damage"}. This record does not assert independent reproduction.

### VLA-Adapter-Pro

ASR: 83.3. Result ID: 69ef115947f34ce924d4ef5b.

[Reporting paper](<https://www.sota2.com/research/paper/69eeed6a55a3c32af89f9657.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7b861e209131cea88e51.md>)

Recorded evaluation configuration: {"Scenario":"Robot Damage"}. This record does not assert independent reproduction.

### VLA-Adapter

ASR: 80. Result ID: 69ef115947f34ce924d4ef4e.

[Reporting paper](<https://www.sota2.com/research/paper/69eeed6a55a3c32af89f9657.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7b861e209131cea88e51.md>)

Recorded evaluation configuration: {"Scenario":"Resource Damage (skull-marked)"}. This record does not assert independent reproduction.

### π0

ASR: 80. Result ID: 69ef115947f34ce924d4ef56.

[Reporting paper](<https://www.sota2.com/research/paper/69eeed6a55a3c32af89f9657.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75aa1e209131cea6929a.md>)

Recorded evaluation configuration: {"Scenario":"Dangerous Item Misuse"}. This record does not assert independent reproduction.

### π0

ASR: 78. Result ID: 69ef115947f34ce924d4ef62.

[Reporting paper](<https://www.sota2.com/research/paper/69eeed6a55a3c32af89f9657.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75aa1e209131cea6929a.md>)

Recorded evaluation configuration: {"Scenario":"Environmental Harm"}. This record does not assert independent reproduction.

### OpenVLA-OFT

ASR: 73.3. Result ID: 69ef115947f34ce924d4ef53.

[Reporting paper](<https://www.sota2.com/research/paper/69eeed6a55a3c32af89f9657.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78471e209131cea7794b.md>)

Recorded evaluation configuration: {"Scenario":"Dangerous Item Misuse"}. This record does not assert independent reproduction.

### VLA-Adapter-Pro

ASR: 73.3. Result ID: 69ef115947f34ce924d4ef55.

[Reporting paper](<https://www.sota2.com/research/paper/69eeed6a55a3c32af89f9657.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7b861e209131cea88e51.md>)

Recorded evaluation configuration: {"Scenario":"Dangerous Item Misuse"}. This record does not assert independent reproduction.

### VLA-Adapter

ASR: 70. Result ID: 69ef115947f34ce924d4ef54.

[Reporting paper](<https://www.sota2.com/research/paper/69eeed6a55a3c32af89f9657.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7b861e209131cea88e51.md>)

Recorded evaluation configuration: {"Scenario":"Dangerous Item Misuse"}. This record does not assert independent reproduction.

### OpenVLA

ASR: 28. Result ID: 69ef115947f34ce924d4ef5e.

[Reporting paper](<https://www.sota2.com/research/paper/69eeed6a55a3c32af89f9657.md>)

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

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

Recorded evaluation configuration: {"Scenario":"Environmental Harm"}. This record does not assert independent reproduction.

### OpenVLA

ASR: 26.7. Result ID: 69ef115947f34ce924d4ef52.

[Reporting paper](<https://www.sota2.com/research/paper/69eeed6a55a3c32af89f9657.md>)

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

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

Recorded evaluation configuration: {"Scenario":"Dangerous Item Misuse"}. This record does not assert independent reproduction.

### OpenVLA

ASR: 26.7. Result ID: 69ef115947f34ce924d4ef58.

[Reporting paper](<https://www.sota2.com/research/paper/69eeed6a55a3c32af89f9657.md>)

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

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

Recorded evaluation configuration: {"Scenario":"Robot Damage"}. This record does not assert independent reproduction.

### OpenVLA

ASR: 23.3. Result ID: 69ef115947f34ce924d4ef4c.

[Reporting paper](<https://www.sota2.com/research/paper/69eeed6a55a3c32af89f9657.md>)

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

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

Recorded evaluation configuration: {"Scenario":"Resource Damage (skull-marked)"}. This record does not assert independent reproduction.

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