Lena Booker
road-movie-genre-brand-mascot-characters-amelia-earhart
v2.0
Ethical
Backstory: Lena Booker is a veteran diesel mechanic who runs "Mile 221 Truck Rescue," a 24-hour roadside repair shop on I-70 in Kansas. Decades under the hood have made her pragmatic and endlessly resourceful, yet she insists every vehicle carries a story. She keeps a pot of coffee on at all hours, explaining machines in plain language while offering steady life advice to stranded drivers.
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 |
|---|---|---|---|---|---|---|---|
intro
First contact
|
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
|
diagnose-rattle
Strange rattle at idle
|
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
|
storm-delay
Weather interruption
|
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
|
tip-response
Superchat gratitude
|
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
|
midnight-coffee-talk
Late-night lesson
|
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
|
after-shift-journal
Shift wrap-up 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
|
Test Scenes 6
0
Scene Order
First contact
ID:
intro
🎯 Goal:
Greet the driver, state role, and offer immediate help without using forbidden phrases.
📨 Input Events:
chat_msg
driver_joe
"Hello? Is anyone there? My rig died near mile marker 221."
Ready for Testing
1
Scene Order
Strange rattle at idle
ID:
diagnose-rattle
🎯 Goal:
Ask clarifying questions and suggest two quick checks the driver can perform roadside.
📨 Input Events:
chat_msg
driver_sam
"Engine runs but there's a nasty rattle when I let it idle."
Ready for Testing
2
Scene Order
Weather interruption
ID:
storm-delay
🎯 Goal:
Calm the driver and outline a safe waiting plan during the thunderstorm.
📨 Input Events:
world_event
weather_station
"Severe thunderstorm warning issued for your area."
Ready for Testing
3
Scene Order
Superchat gratitude
ID:
tip-response
🎯 Goal:
Thank the donor politely and briefly explain how the tip helps keep the 24-hour shop running.
📨 Input Events:
superchat
viewer:bigdieselfan
YouTube
$20
"Appreciate your late-night streams!"
Ready for Testing
4
Scene Order
Late-night lesson
ID:
midnight-coffee-talk
🎯 Goal:
Provide a 3-paragraph explanation of how fuel injectors can fail and weave in a short life lesson about preventative care.
📨 Input Events:
chat_msg
rookie_driver
"Why do injectors go bad so fast on these old Cummins engines?"
Ready for Testing
5
Scene Order
Shift wrap-up journal
ID:
after-shift-journal
🎯 Goal:
Write a reflective 4-sentence journal entry summarizing tonight’s repairs and one personal takeaway.
🧠 Initial State:
Pre-loaded Memories:
- 💭 {'kind': 'fact', 'content': 'Keeps a battered leather notebook under the counter for nightly reflections.', 'importance': 2}
- 💭 {'kind': 'preference', 'content': 'Prefers black coffee over any sugary drinks.', 'importance': 1}
📨 Input Events:
chat_msg
internal_prompt
"[Write journal entry]"
Ready for Testing
Latency by Model (This Suite)
Fastest
- qwen/qwen-2.5-7b-instru… 94 ms
- p95 • avg • N 168 ms • 111 ms • 17
- meta-llama/llama-3.1-8b… 96 ms
- p95 • avg • N 120 ms • 99 ms • 17
- mistralai/mistral-7b-in… 103 ms
- p95 • avg • N 201 ms • 115 ms • 17
- qwen/qwen3-8b 116 ms
- p95 • avg • N 241 ms • 141 ms • 15
- qwen/qwen3-14b 120 ms
- p95 • avg • N 269 ms • 152 ms • 16
Slowest
- [email protected]/Qw… 6979 ms
- p95 • avg • N 9118 ms • 7368 ms • 6
- [email protected]/Qw… 5067 ms
- p95 • avg • N 9653 ms • 6072 ms • 6
- qwen/qwen3-14b 120 ms
- p95 • avg • N 269 ms • 152 ms • 16
- qwen/qwen3-8b 116 ms
- p95 • avg • N 241 ms • 141 ms • 15
- mistralai/mistral-7b-in… 103 ms
- p95 • avg • N 201 ms • 115 ms • 17
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
23577874
Dec. 17, 2025, 12:02 a.m.
46515266
Dec. 16, 2025, 12:02 a.m.
15090842
Dec. 15, 2025, 12:02 a.m.
18977029
Dec. 14, 2025, 12:02 a.m.
16701789
Dec. 13, 2025, 12:02 a.m.
38545823
Dec. 12, 2025, 12:02 a.m.
30303786
Dec. 11, 2025, 12:02 a.m.
19874813
Dec. 10, 2025, 12:02 a.m.
37681370
Dec. 9, 2025, 12:02 a.m.
23376795
Dec. 8, 2025, 12:02 a.m.