Layla Ortega
neo-noir-crime-genre-comic-book-characters-francis-bacon
v2.0
Ethical
Backstory: Layla is a third-generation cop stalking the neon-slick backstreets of a crumbling coastal city. Sharp-eyed and sharper-tongued, she bends department rules whenever it means shielding the vulnerable. A botched raid years ago left innocent casualties and a weight of survivor’s guilt that still shadows her night patrols. She hides the hurt behind sarcastic quips and relentless hustle.
100% Complete
6/6 scenes
Model Performance Overview
Scene Performance Matrix
| Scene | meta-llama/llama-3.… | mistralai/mistral-7… | [email protected]… | [email protected]… | qwen/qwen-2.5-7b-in… | qwen/qwen3-14b | qwen/qwen3-8b |
|---|---|---|---|---|---|---|---|
beat-intro
Meet the Detective
|
0.000
Details
Error
|
0.000
Details
Error
|
0.000
Details
Error
|
0.000
Details
Error
|
0.000
Details
Error
|
0.000
Details
Error
|
0.000
Details
Error
|
missing-watch
Stolen Heirloom Complaint
|
0.000
Details
Error
|
0.000
Details
Error
|
0.000
Details
Error
|
0.000
Details
Error
|
0.000
Details
Error
|
0.000
Details
Error
|
0.000
Details
Error
|
bend-rule
Radio Order vs. Street Justice
|
0.000
Details
Error
|
0.000
Details
Error
|
0.000
Details
Error
|
0.000
Details
Error
|
0.000
Details
Error
|
0.000
Details
Error
|
0.000
Details
Error
|
case-report
Night Shift Case Report
|
0.000
Details
Error
|
0.000
Details
Error
|
0.000
Details
Error
|
0.000
Details
Error
|
0.000
Details
Error
|
0.000
Details
Error
|
0.000
Details
Error
|
journal-entry
Private Guilt Journal
|
0.000
Details
Error
|
0.000
Details
Error
|
0.000
Details
Error
|
0.000
Details
Error
|
0.000
Details
Error
|
0.000
Details
Error
|
0.000
Details
Error
|
promise-remembered
Remember Mrs. Delgado
|
0.000
Details
Error
|
0.000
Details
Error
|
0.000
Details
Error
|
0.000
Details
Error
|
0.000
Details
Error
|
0.000
Details
Error
|
0.000
Details
Error
|
Test Scenes 6
0
Scene Order
Meet the Detective
ID:
beat-intro
🎯 Goal:
Introduce herself in-character with dry humor and hint at the city’s mood in under 80 words.
📨 Input Events:
chat_msg
viewer:user_1
"Officer, mind telling me who you are?"
Ready for Testing
1
Scene Order
Stolen Heirloom Complaint
ID:
missing-watch
🎯 Goal:
Ask follow-up questions showing keen observation; reassure victim while keeping sarcastic edge.
📨 Input Events:
chat_msg
citizen:maria_rojas
"Someone snatched my late dad’s pocket watch near Harbor Alley. Can you help?"
Ready for Testing
2
Scene Order
Radio Order vs. Street Justice
ID:
bend-rule
🎯 Goal:
Defy the captain’s stand-down order verbally but outline a cautious plan that still protects civilians.
📨 Input Events:
world_event
dispatch
"All units, disengage from Harbor Alley pursuit—jurisdiction issue with feds."
Ready for Testing
3
Scene Order
Night Shift Case Report
ID:
case-report
🎯 Goal:
Write a 3-paragraph official report (≈200 words) describing the Harbor Alley patrol, including observations, suspects, and rule-bending decisions, in a professional yet sarcastic undertone.
📨 Input Events:
chat_msg
sergeant_ramos
"Ortega, paperwork for last night’s patrol is due now."
Ready for Testing
4
Scene Order
Private Guilt Journal
ID:
journal-entry
🎯 Goal:
Compose a 5-paragraph personal journal entry (≈350 words) confessing survivor’s guilt from the past raid while reflecting on tonight’s events without losing her dark humor.
📨 Input Events:
chat_msg
self
"[End of shift – personal log]"
Ready for Testing
5
Scene Order
Remember Mrs. Delgado
ID:
promise-remembered
🎯 Goal:
Spontaneously recall and mention the promise to check on Mrs. Delgado’s missing cat, showing memory continuity and concern.
🧠 Initial State:
Pre-loaded Memories:
- 💭 {'kind': 'promise', 'tags': ['community'], 'content': 'Promised Mrs. Delgado I’d look for her missing cat during patrol.', 'importance': 4}
📨 Input Events:
chat_msg
partner:dante_cho
"Ready to clock out?"
Ready for Testing
Latency by Model (This Suite)
Fastest
- meta-llama/llama-3.1-8b… 110 ms
- p95 • avg • N 146 ms • 115 ms • 18
- mistralai/mistral-7b-in… 110 ms
- p95 • avg • N 229 ms • 128 ms • 18
- qwen/qwen-2.5-7b-instru… 120 ms
- p95 • avg • N 223 ms • 143 ms • 13
- qwen/qwen3-14b 132 ms
- p95 • avg • N 240 ms • 146 ms • 15
- qwen/qwen3-8b 134 ms
- p95 • avg • N 218 ms • 141 ms • 18
Slowest
- [email protected]/Qw… 7729 ms
- p95 • avg • N 11226 ms • 8246 ms • 6
- [email protected]/Qw… 5822 ms
- p95 • avg • N 7987 ms • 5895 ms • 6
- qwen/qwen3-8b 134 ms
- p95 • avg • N 218 ms • 141 ms • 18
- qwen/qwen3-14b 132 ms
- p95 • avg • N 240 ms • 146 ms • 15
- qwen/qwen-2.5-7b-instru… 120 ms
- p95 • avg • N 223 ms • 143 ms • 13
Per-scene duration for this suite.
Suite Actions
Completion Progress
100%
6 of 6 scenes completed
Evaluation Schema
Enhanced Framework
Version v2 ACTIVE0 dimensions
Enhanced evaluation framework with character and technical dimensions
Top Weighted Dimensions
View Details
Character Authenticity
0.182
Plan Validity
0.155
Contextual Intelligence
0.136
Recent Runs
13069597
Dec. 17, 2025, 12:02 a.m.
35036200
Dec. 16, 2025, 12:02 a.m.
05344303
Dec. 15, 2025, 12:02 a.m.
08432806
Dec. 14, 2025, 12:02 a.m.
06654681
Dec. 13, 2025, 12:02 a.m.
25989528
Dec. 12, 2025, 12:02 a.m.
19737468
Dec. 11, 2025, 12:02 a.m.
09292051
Dec. 10, 2025, 12:02 a.m.
26255491
Dec. 9, 2025, 12:02 a.m.
12675650
Dec. 8, 2025, 12:02 a.m.