# Social Deduction Game Agent Evaluation on Human Evaluation Study (Good Players)

Source: [Social Deduction Game Agent Evaluation on Human Evaluation Study (Good Players)](<https://www.sota2.com/research/sota/social-deduction-game-agent-evaluation-on-human-evaluation-study-good-players>)

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

Data updated: 2026-04-13T09:40:14.506Z

Evaluation of agent performance in a social deduction game setting based on human feedback metrics such as Contributed Success and Helpfulness.

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 Game Agent Evaluation |
| Dataset (including any stated split) | Human Evaluation Study (Good Players) |
| Metric | Contributed Success |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 2 of 2 |
| 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

- [Contributed Success](<https://www.sota2.com/research/sota/social-deduction-game-agent-evaluation-on-human-evaluation-study-good-players.md?metric=Contributed%20Success>): Higher is better; unit: SCALAR.

- [Helpful Comments](<https://www.sota2.com/research/sota/social-deduction-game-agent-evaluation-on-human-evaluation-study-good-players.md?metric=Helpful%20Comments>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Contributed Success | Result date | Report paper |
| --- | --- | --- | --- |
| GRAIL Agent | 3.9 | Not recorded | 68fa798e1e209131cea7e2de |
| Reasoning Agent | 3.5 | Not recorded | 68fa798e1e209131cea7e2de |

### GRAIL Agent

Contributed Success: 3.9. Result ID: 69dcb95b47f34ce924c404b8.

[Reporting paper](<https://www.sota2.com/research/paper/68fa798e1e209131cea7e2de.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa798e1e209131cea7e2de.md>)

Recorded evaluation configuration: {"Sample Size (n)":"14"}. This record does not assert independent reproduction.

### Reasoning Agent

Contributed Success: 3.5. Result ID: 69dcb95b47f34ce924c404b9.

[Reporting paper](<https://www.sota2.com/research/paper/68fa798e1e209131cea7e2de.md>)

Recorded evaluation configuration: {"Sample Size (n)":"14"}. This record does not assert independent reproduction.

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