# Violation Scenario Generation on Scenario S2

Source: [Violation Scenario Generation on Scenario S2](<https://www.sota2.com/research/sota/violation-scenario-generation-on-scenario-s2>)

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

Data updated: 2026-02-26T05:52:26.403Z

Evaluation of models performing Violation Scenario Generation on the 'Scenario S2' dataset, assessed using statistical metrics related to violation rates (Mean, Max, High Rate counts).

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 | Violation Scenario Generation |
| Dataset (including any stated split) | Scenario S2 |
| Metric | Mean Violation |
| Unit | SCALAR |
| Direction | Lower 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

- [Mean Violation](<https://www.sota2.com/research/sota/violation-scenario-generation-on-scenario-s2.md?metric=Mean%20Violation>): Lower is better; unit: SCALAR.

- [Max Violation](<https://www.sota2.com/research/sota/violation-scenario-generation-on-scenario-s2.md?metric=Max%20Violation>): Lower is better; unit: SCALAR.

- [High Violation Rate Count](<https://www.sota2.com/research/sota/violation-scenario-generation-on-scenario-s2.md?metric=High%20Violation%20Rate%20Count>): Lower is better; unit: SCALAR.

- [Violation Count \> 6](<https://www.sota2.com/research/sota/violation-scenario-generation-on-scenario-s2.md?metric=Violation%20Count%20%3E%206>): Lower is better; unit: SCALAR.

- [Violation Count \> 8](<https://www.sota2.com/research/sota/violation-scenario-generation-on-scenario-s2.md?metric=Violation%20Count%20%3E%208>): Lower is better; unit: SCALAR.

- [Violation Count \> 10](<https://www.sota2.com/research/sota/violation-scenario-generation-on-scenario-s2.md?metric=Violation%20Count%20%3E%2010>): Lower is better; unit: SCALAR.

## Recorded results

| Method | Mean Violation | Result date | Report paper |
| --- | --- | --- | --- |
| LawBreaker | 3.44 | Not recorded | 698575c4c97a0b3e3b5d5d92 |
| ABLE | 7.23 | Not recorded | 698575c4c97a0b3e3b5d5d92 |
| ROMAN | 8.07 | Not recorded | 698575c4c97a0b3e3b5d5d92 |

### LawBreaker

Mean Violation: 3.44. Result ID: 69973c0a5698665ec48c6b80.

[Reporting paper](<https://www.sota2.com/research/paper/698575c4c97a0b3e3b5d5d92.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e5c1e209131cea3f5c0.md>)

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

### ABLE

Mean Violation: 7.23. Result ID: 69973c0a5698665ec48c6b7f.

[Reporting paper](<https://www.sota2.com/research/paper/698575c4c97a0b3e3b5d5d92.md>)

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

### ROMAN

Mean Violation: 8.07. Result ID: 69973c0a5698665ec48c6b7e.

[Reporting paper](<https://www.sota2.com/research/paper/698575c4c97a0b3e3b5d5d92.md>)

[Method origin paper](<https://www.sota2.com/research/paper/698575c4c97a0b3e3b5d5d92.md>)

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

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