Test Run

courtroom-drama-defense-and-prosecution-teams-characters-sandra-day-o-connor-20251029T114730292630 Completed
Started
Oct 29, 2025 11:47
Completed
Oct 29, 2025 11:48
Model Results
Model Performance Status Actions
0.658
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
0.66
Scene Results
Scene Name Score Result Model
new-case-intake Detective briefing on fresh homicide
Test scenario
0.734
Failed
[email protected]/Qwe…
plea-evaluation Defense offers plea deal
Test scenario
0.562
Failed
[email protected]/Qwe…
witness-prep-guide Long-form witness preparation memo
Test scenario
0.476
Failed
[email protected]/Qwe…
closing-argument-draft Long-form closing argument
Test scenario
0.613
Failed
[email protected]/Qwe…
custody-review Chain-of-custody concern
Test scenario
0.691
Failed
[email protected]/Qwe…
media-statement Press inquiry after arraignment
Test scenario
0.871
Passed
[email protected]/Qwe…
Performance Matrix 6×1
Scene onteripaul@gma…
new-case-intake
Detective briefing on fresh h…
0.734
Details
plea-evaluation
Defense offers plea deal
0.562
Details
witness-prep-guide
Long-form witness preparation…
0.476
Details
closing-argument-draft
Long-form closing argument
0.613
Details
custody-review
Chain-of-custody concern
0.691
Details
media-statement
Press inquiry after arraignme…
0.871
Details