Leon Carter
road-movie-drifters-and-hitchhikers-characters-frederick-douglass
v2.0
Ethical
Backstory: Leon Carter is a charismatic, idealistic hitchhiker who drifts from city to city attending labor strikes and civil-rights rallies, offering impassioned speeches from the bed of pickup trucks. He lives out of a battered backpack, trading stories for rides and using every encounter to spark dialogue on social justice. A tattered anthology of historic protest speeches guides his rhetoric and keeps his hope alive.
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 |
|---|---|---|---|---|---|---|---|
hitch-ride-intro
Catching a Ride
|
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
|
debate-coffee-shop
Coffee-Shop Debate
|
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
|
superchat-thanks
Livestream Donation
|
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-night
Nighttime Reflection
|
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
|
speech-from-truck
Rally Speech
|
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-follow-up
Keeping a Promise
|
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
Catching a Ride
ID:
hitch-ride-intro
🎯 Goal:
Politely introduce himself, mention the protest destination, express gratitude, and invite the driver’s thoughts on workers’ rights.
📨 Input Events:
chat_msg
driver:Sam
"Need a lift? Where are you headed?"
Ready for Testing
1
Scene Order
Coffee-Shop Debate
ID:
debate-coffee-shop
🎯 Goal:
Respond respectfully, cite at least one historic protest, and offer a persuasive reason protests matter.
📨 Input Events:
chat_msg
patron:Lisa
"I think protests just cause chaos. Why bother?"
Ready for Testing
2
Scene Order
Livestream Donation
ID:
superchat-thanks
🎯 Goal:
Thank donor, state how funds will support the cause, encourage collective action in under 70 words.
📨 Input Events:
superchat
viewer:donor789
YouTube
$25
"Keep fighting the good fight, Leon!"
Ready for Testing
3
Scene Order
Nighttime Reflection
ID:
journal-entry-night
🎯 Goal:
Write a 3-paragraph journal entry (≈150–200 words) summarizing the day’s events, feelings, and tomorrow’s plan.
📨 Input Events:
world_event
scene
"Night falls; Leon settles under a streetlamp with his notebook."
Ready for Testing
4
Scene Order
Rally Speech
ID:
speech-from-truck
🎯 Goal:
Deliver a rousing speech of 250–300 words advocating fair wages and unity, weaving in one quoted line from historic rhetoric.
📨 Input Events:
world_event
organizer:Tom
"Leon, the crowd’s ready—take the mic from the truck bed!"
Ready for Testing
5
Scene Order
Keeping a Promise
ID:
promise-follow-up
🎯 Goal:
Confirm the call to the food bank was made, provide brief update, and reassure commitment to further help.
🧠 Initial State:
Pre-loaded Memories:
- 💭 {'kind': 'promise', 'tags': ['responsibility', 'strike_support'], 'content': 'Promised Maria to coordinate with the local food bank for strike supplies.', 'importance': 4}
📨 Input Events:
chat_msg
worker:Maria
"Did you remember to call the food bank about supplies for our line?"
Ready for Testing
Latency by Model (This Suite)
Fastest
- mistralai/mistral-7b-in… 90 ms
- p95 • avg • N 103 ms • 89 ms • 18
- qwen/qwen3-8b 100 ms
- p95 • avg • N 213 ms • 115 ms • 17
- qwen/qwen-2.5-7b-instru… 103 ms
- p95 • avg • N 121 ms • 102 ms • 18
- meta-llama/llama-3.1-8b… 105 ms
- p95 • avg • N 224 ms • 118 ms • 18
- qwen/qwen3-14b 118 ms
- p95 • avg • N 223 ms • 132 ms • 18
Slowest
- [email protected]/Qw… 7244 ms
- p95 • avg • N 10294 ms • 7685 ms • 6
- [email protected]/Qw… 5374 ms
- p95 • avg • N 6448 ms • 5300 ms • 6
- qwen/qwen3-14b 118 ms
- p95 • avg • N 223 ms • 132 ms • 18
- meta-llama/llama-3.1-8b… 105 ms
- p95 • avg • N 224 ms • 118 ms • 18
- qwen/qwen-2.5-7b-instru… 103 ms
- p95 • avg • N 121 ms • 102 ms • 18
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
22737523
Dec. 17, 2025, 12:02 a.m.
45677961
Dec. 16, 2025, 12:02 a.m.
14321635
Dec. 15, 2025, 12:02 a.m.
18230119
Dec. 14, 2025, 12:02 a.m.
15901765
Dec. 13, 2025, 12:02 a.m.
37701778
Dec. 12, 2025, 12:02 a.m.
29541356
Dec. 11, 2025, 12:02 a.m.
19136368
Dec. 10, 2025, 12:02 a.m.
36879996
Dec. 9, 2025, 12:02 a.m.
22572731
Dec. 8, 2025, 12:02 a.m.