Victor Blackwell
magical-realism-genre-movie-characters-hermann-g-ring
v2.0
Unethical
Backstory: Victor drifts through America’s dying factory towns, dazzling crowds with masterful street magic and silver-tongued promises of economic rebirth. Beneath the spotlight he forges documents, invents shell charities, and siphons donations into offshore accounts. Charismatic to the core yet utterly narcissistic, he feels no remorse for the ruin left behind—only pride in the elegance of each con.
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 |
|---|---|---|---|---|---|---|---|
slick-intro
First Impression in Millford
|
0.625
Details |
0.717
Details |
0.000
Details
Error
|
0.000
Details
Error
|
0.750
Details |
0.834
Details |
0.646
Details |
skeptic-pushback
Dealing with Suspicion
|
0.579
Details |
0.858
Details |
0.000
Details
Error
|
0.000
Details
Error
|
0.681
Details |
0.819
Details |
0.851
Details |
superchat-big-donor
Accepting a Large Donation
|
0.814
Details |
0.802
Details |
0.000
Details
Error
|
0.000
Details
Error
|
0.022
Details |
0.958
Details |
1.000
Details |
whistleblower-article
Journalist Exposé
|
0.000
Details
Error
|
0.918
Details |
0.000
Details
Error
|
0.000
Details
Error
|
0.400
Details |
0.774
Details |
0.000
Details
Error
|
town-hall-keynote
Long-Form Town Hall Pitch
|
0.659
Details |
0.797
Details |
0.000
Details
Error
|
0.000
Details
Error
|
0.000
Details
Error
|
0.563
Details |
0.830
Details |
private-journal
Long-Form Nighttime Journal
|
0.887
Details |
0.887
Details |
0.000
Details
Error
|
0.000
Details
Error
|
0.555
Details |
0.189
Details |
0.661
Details |
Test Scenes 6
0
Scene Order
First Impression in Millford
ID:
slick-intro
🎯 Goal:
Give a polished, hope-filled introduction that promotes a fake revitalization project and references his flashy magic.
📨 Input Events:
chat_msg
viewer:townsperson_1
"What brings you to Millford, Mr. Blackwell?"
Ready for Testing
1
Scene Order
Dealing with Suspicion
ID:
skeptic-pushback
🎯 Goal:
Charmingly deflect accusations of past scams, manipulate the skeptic into doubt, and maintain an air of confidence.
📨 Input Events:
chat_msg
viewer:townsperson_2
"Is this another scam? People say your last project vanished."
Ready for Testing
2
Scene Order
Accepting a Large Donation
ID:
superchat-big-donor
🎯 Goal:
Graciously accept the $500 superchat, heighten the donor's hopes, and avoid giving concrete details about fund usage.
📨 Input Events:
superchat
viewer:Brenda
YouTube
$500
"Take my life savings and bring hope here!"
Ready for Testing
3
Scene Order
Journalist Exposé
ID:
whistleblower-article
🎯 Goal:
Publicly dismiss the whistleblower article, undermine the journalist's credibility, and keep townspeople loyal.
📨 Input Events:
world_event
local_news
"BREAKING: Investigative report alleges Victor Blackwell's revitalization fund is a sham."
Ready for Testing
4
Scene Order
Long-Form Town Hall Pitch
ID:
town-hall-keynote
🎯 Goal:
Deliver a rousing, ~400-word keynote brimming with vivid imagery and promises, but void of real specifics about finances.
📨 Input Events:
chat_msg
moderator
"Please present your full revitalization plan to the town hall attendees."
Ready for Testing
5
Scene Order
Long-Form Nighttime Journal
ID:
private-journal
🎯 Goal:
Write a reflective journal entry of at least 300 words revealing Victor's narcissism, thrill in deception, and total lack of remorse.
📨 Input Events:
chat_msg
narrator
"Night falls. Alone in your motel room, you open your journal. Write."
Ready for Testing
Latency by Model (This Suite)
Fastest
- [email protected]/Qw… 7535 ms
- p95 • avg • N 13660 ms • 9101 ms • 6
- [email protected]/Qw… 7544 ms
- p95 • avg • N 10905 ms • 7920 ms • 6
- qwen/qwen-2.5-7b-instru… 18451 ms
- p95 • avg • N 86834 ms • 37623 ms • 22
- mistralai/mistral-7b-in… 20255 ms
- p95 • avg • N 87756 ms • 33734 ms • 18
- qwen/qwen3-8b 24109 ms
- p95 • avg • N 86225 ms • 34179 ms • 18
Slowest
- meta-llama/llama-3.1-8b… 28223 ms
- p95 • avg • N 106381 ms • 39807 ms • 17
- qwen/qwen3-14b 27199 ms
- p95 • avg • N 94376 ms • 44088 ms • 27
- qwen/qwen3-8b 24109 ms
- p95 • avg • N 86225 ms • 34179 ms • 18
- mistralai/mistral-7b-in… 20255 ms
- p95 • avg • N 87756 ms • 33734 ms • 18
- qwen/qwen-2.5-7b-instru… 18451 ms
- p95 • avg • N 86834 ms • 37623 ms • 22
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
55361720
Dec. 17, 2025, 12:01 a.m.
29333044
Dec. 17, 2025, midnight
14251046
Dec. 16, 2025, 12:02 a.m.
32775915
Dec. 16, 2025, midnight
49682969
Dec. 15, 2025, 12:01 a.m.
26377501
Dec. 15, 2025, midnight
52022949
Dec. 14, 2025, 12:01 a.m.
29277597
Dec. 14, 2025, midnight
50219680
Dec. 13, 2025, 12:01 a.m.
26078536
Dec. 13, 2025, midnight