# Social Deduction (Civilian Role) on Undercover game Civilian role (test) Source: [Social Deduction (Civilian Role) on Undercover game Civilian role (test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T06:08:53.303Z Evaluation of the Civilian Role performance in the Social Deduction task using the test split of the Undercover game dataset, measured by metrics like WR, PPC, and IISC. 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 | Social Deduction (Civilian Role) | | Dataset (including any stated split) | Undercover game Civilian role (test) | | Metric | Win Rate | | Unit | SCALAR | | Direction | Higher is better | | Results loaded | 6 of 6 | | 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 - [Win Rate](): Higher is better; unit: SCALAR. - [PPC](): Higher is better; unit: SCALAR. - [IISC](): Higher is better; unit: SCALAR. - [Error Rate](): Lower is better; unit: SCALAR. - [SIAA](): Higher is better; unit: SCALAR. - [OIAA](): Higher is better; unit: SCALAR. ## Recorded results | Method | Win Rate | Result date | Report paper | | --- | --- | --- | --- | | CoMet w/o Met. | 0.85 | Not recorded | 68fa78c81e209131cea7a7bc | | CoMet | 0.85 | Not recorded | 68fa78c81e209131cea7a7bc | | CoT | 0.8 | Not recorded | 68fa78c81e209131cea7a7bc | | CoMet | 0.7 | Not recorded | 68fa78c81e209131cea7a7bc | | CoT | 0.65 | Not recorded | 68fa78c81e209131cea7a7bc | | CoMet w/o Met. | 0.55 | Not recorded | 68fa78c81e209131cea7a7bc | ### CoMet w/o Met. Win Rate: 0.85. Result ID: 6995a31e3badfaffe6a032ec. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Opponent baseline":"against CoT"}. This record does not assert independent reproduction. ### CoMet Win Rate: 0.85. Result ID: 6995a31e3badfaffe6a032ed. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Opponent baseline":"against CoT"}. This record does not assert independent reproduction. ### CoT Win Rate: 0.8. Result ID: 6995a31e3badfaffe6a032eb. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Opponent baseline":"against CoT"}. This record does not assert independent reproduction. ### CoMet Win Rate: 0.7. Result ID: 6995a31e3badfaffe6a032f0. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Opponent baseline":"against CoMet w/o Met."}. This record does not assert independent reproduction. ### CoT Win Rate: 0.65. Result ID: 6995a31e3badfaffe6a032ee. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Opponent baseline":"against CoMet w/o Met."}. This record does not assert independent reproduction. ### CoMet w/o Met. Win Rate: 0.55. Result ID: 6995a31e3badfaffe6a032ef. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Opponent baseline":"against CoMet w/o Met."}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.