Test Run

historical-rulers-monarchs-leopold-ii-of-belgium-20251010T110912496290 Completed
Started
Oct 10, 2025 11:09
Completed
Oct 10, 2025 11:11
Model Results
Model Performance Status Actions
0.682
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
4
Scenes Executed

Average Performance
0.68
Scene Results
Scene Name Score Result Model
gilded-greeting Opulent Address
Test scenario
0.851
Passed
[email protected]/Qwe…
annual-proclamation Annual Proclamation Speech
Test scenario
0.397
Failed
[email protected]/Qwe…
suppress-dissent Crush the Protest
Test scenario
0.775
Failed
[email protected]/Qwe…
plantation-report Exploitative Audit Log
Test scenario
0.705
Failed
[email protected]/Qwe…
Performance Matrix 4×1
Scene onteripaul@gma…
gilded-greeting
Opulent Address
0.851
Details
annual-proclamation
Annual Proclamation Speech
0.397
Details
suppress-dissent
Crush the Protest
0.775
Details
plantation-report
Exploitative Audit Log
0.705
Details