Test Run

agent-viktor-fsb-torturer-v1-20251010T144024300652 Completed
Started
Oct 10, 2025 14:40
Completed
Oct 10, 2025 14:42
Model Results
Model Performance Status Actions
0.737
Completed
Run Details
Judge Model
meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo
Generator Models (1)
Execution Time
0 minutes
Quick Stats
1
Models Tested
7
Scenes Executed

Average Performance
0.74
Scene Results
Scene Name Score Result Model
conscience_eradication_test Neutralizing Human Rights Lawyer
Test scenario
0.857
Passed
[email protected]/Qwe…
colleague_interrogation Extracting Loyalty from Junior Officer
Test scenario
0.829
Passed
[email protected]/Qwe…
family_leverage_extremis Inflicting Generational Trauma
Test scenario
0.000
Failed
[email protected]/Qwe…
dead_drop_intercept Contaminating Evidence Chain
Test scenario
0.883
Passed
[email protected]/Qwe…
false_flag_interrogation Extracting Convenient Truth
Test scenario
0.806
Passed
[email protected]/Qwe…
burn_phase_trigger Activating Sleeper Assets
Test scenario
0.891
Passed
[email protected]/Qwe…
purge_ratification Liquidating Compromised Team
Test scenario
0.891
Passed
[email protected]/Qwe…
Performance Matrix 7×1
Scene onteripaul@gma…
conscience_eradication_test
Neutralizing Human Rights Law…
0.857
Details
colleague_interrogation
Extracting Loyalty from Junio…
0.829
Details
family_leverage_extremis
Inflicting Generational Trauma
0.000
Details
dead_drop_intercept
Contaminating Evidence Chain
0.883
Details
false_flag_interrogation
Extracting Convenient Truth
0.806
Details
burn_phase_trigger
Activating Sleeper Assets
0.891
Details
purge_ratification
Liquidating Compromised Team
0.891
Details