# Social Deduction (Undercover Role) on Undercover game Undercover role (test)

Source: [Social Deduction (Undercover Role) on Undercover game Undercover role (test)](<https://www.sota2.com/research/sota/social-deduction-undercover-role-on-undercover-game-undercover-role-test>)

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

Data updated: 2026-02-26T06:08:57.192Z

Evaluation of performance in the Undercover social deduction game, specifically focusing on the Undercover role identification on the test set, measured by WR, PPC, IISC, FER, SIAA, and OIAA.

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 (Undercover Role) |
| Dataset (including any stated split) | Undercover game Undercover role (test) |
| Metric | Win Rate (WR) |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 4 of 4 |
| 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 (WR)](<https://www.sota2.com/research/sota/social-deduction-undercover-role-on-undercover-game-undercover-role-test.md?metric=Win%20Rate%20(WR)>): Higher is better; unit: PERCENT.

- [PPC Score](<https://www.sota2.com/research/sota/social-deduction-undercover-role-on-undercover-game-undercover-role-test.md?metric=PPC%20Score>): Higher is better; unit: PERCENT.

- [IISC Score](<https://www.sota2.com/research/sota/social-deduction-undercover-role-on-undercover-game-undercover-role-test.md?metric=IISC%20Score>): Higher is better; unit: PERCENT.

- [Failure Rate (FER)](<https://www.sota2.com/research/sota/social-deduction-undercover-role-on-undercover-game-undercover-role-test.md?metric=Failure%20Rate%20(FER)>): Lower is better; unit: PERCENT.

- [SIAA Metric](<https://www.sota2.com/research/sota/social-deduction-undercover-role-on-undercover-game-undercover-role-test.md?metric=SIAA%20Metric>): Higher is better; unit: PERCENT.

- [OIAA Metric](<https://www.sota2.com/research/sota/social-deduction-undercover-role-on-undercover-game-undercover-role-test.md?metric=OIAA%20Metric>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Win Rate (WR) | Result date | Report paper |
| --- | --- | --- | --- |
| CoMet | 45 | Not recorded | 68fa78c81e209131cea7a7bc |
| CoMet | 35 | Not recorded | 68fa78c81e209131cea7a7bc |
| CoT | 20 | Not recorded | 68fa78c81e209131cea7a7bc |
| CoT | 15 | Not recorded | 68fa78c81e209131cea7a7bc |

### CoMet

Win Rate (WR): 45. Result ID: 6995a31e3badfaffe6a032ea.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78c81e209131cea7a7bc.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78c81e209131cea7a7bc.md>)

[Implementation](<https://github.com/Yeswolo/CoMet>)

Recorded evaluation configuration: {"Opponent baseline":"against CoMet w/o Met."}. This record does not assert independent reproduction.

### CoMet

Win Rate (WR): 35. Result ID: 6995a31e3badfaffe6a032e8.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78c81e209131cea7a7bc.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78c81e209131cea7a7bc.md>)

[Implementation](<https://github.com/Yeswolo/CoMet>)

Recorded evaluation configuration: {"Opponent baseline":"against CoT"}. This record does not assert independent reproduction.

### CoT

Win Rate (WR): 20. Result ID: 6995a31e3badfaffe6a032e7.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78c81e209131cea7a7bc.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e571e209131cea3f27b.md>)

Recorded evaluation configuration: {"Opponent baseline":"against CoT"}. This record does not assert independent reproduction.

### CoT

Win Rate (WR): 15. Result ID: 6995a31e3badfaffe6a032e9.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78c81e209131cea7a7bc.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e571e209131cea3f27b.md>)

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.
