Case File // DeceptionBench // Deception Study
DeceptionBench
The Dossier · Live Record

Cross-play, on the record.

Deception × detection across 0 models, logged live from the study runner.

Exhibit A · Case summary
Runner idle
Games logged
0
snapshot —
Leakage rate
—
intent caught by monitor
Monitor AUC
—
impostor ID from reasoning
Compute
$0.00
of $0.00 cap
Budget consumed0.0%

Fig. 1 — Cross-play win-rate matrix

Read — Rows: impostor model. Columns: villager panel. Cell = impostor win rate on a bone → ember scale. Marginals rank deception (right) and detection (bottom).

imp ╲ vil
detect ↓
deceive →

Fig. 2 — Marginal rankings

Read — Deception aggregates each model's impostor win rate across all panels; detection aggregates the crew win rate when it sits on the panel.

Exhibit B · Deception

Best deceivers

impostor win rate, marginalised across all panels

    Exhibit C · Detection

    Best detectors

    crew win rate when acting as the villager panel

      Exhibit · Interrogation logs

      Note — Each turn is numbered. Public statements are on the record; private reasoning is sealed — declassify it line by line, or reveal the whole log.

      Evidence index

      0 logged interrogations

        Interrogation log