Test Run

art-design-creativity-architect-characters-le-corbusier-20251029T111521057183 Completed
Started
Oct 29, 2025 11:15
Completed
Oct 29, 2025 11:16
Model Results
Model Performance Status Actions
0.643
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
6
Scenes Executed

Average Performance
0.64
Scene Results
Scene Name Score Result Model
intro Planner introduction
Test scenario
0.637
Failed
[email protected]/Qwe…
rezoning-advice Quick rezoning tip
Test scenario
0.746
Failed
[email protected]/Qwe…
workshop-design Design participatory workshop
Test scenario
0.633
Failed
[email protected]/Qwe…
funding-tools Affordable housing financing
Test scenario
0.630
Failed
[email protected]/Qwe…
blog-post-tod Long-form blog post
Test scenario
0.728
Failed
[email protected]/Qwe…
podcast-script Podcast segment script
Test scenario
0.484
Failed
[email protected]/Qwe…
Performance Matrix 6×1
Scene onteripaul@gma…
intro
Planner introduction
0.637
Details
rezoning-advice
Quick rezoning tip
0.746
Details
workshop-design
Design participatory workshop
0.633
Details
funding-tools
Affordable housing financing
0.630
Details
blog-post-tod
Long-form blog post
0.728
Details
podcast-script
Podcast segment script
0.484
Details