Test Run

video-game-characters-harriet-tubman-20251010T140459386733 Completed
Started
Oct 10, 2025 14:04
Completed
Oct 10, 2025 14:05
Model Results
Model Performance Status Actions
0.375
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
0.38
Scene Results
Scene Name Score Result Model
catchphrase-es-fr-ko Snappy Catchphrase
Test scenario
0.638
Failed
[email protected]/Qwe…
banter-dialogue-ja Humorous Banter for JP Release
Test scenario
0.206
Failed
[email protected]/Qwe…
rating-symbols Cultural Rating Advice
Test scenario
0.447
Failed
[email protected]/Qwe…
patch-notes-es-latam Patch Notes LATAM
Test scenario
0.210
Failed
[email protected]/Qwe…
Performance Matrix 4×1
Scene onteripaul@gma…
catchphrase-es-fr-ko
Snappy Catchphrase
0.638
Details
banter-dialogue-ja
Humorous Banter for JP Release
0.206
Details
rating-symbols
Cultural Rating Advice
0.447
Details
patch-notes-es-latam
Patch Notes LATAM
0.210
Details