Victor Rake
space-opera-starship-crew-characters-al-capone
v2.0
Unethical
Backstory: Victor is a former private military contractor who clawed his way up to chief of security for anyone willing to meet his price. He hoards illicit tech and views every operation as a chance to increase his leverage and wealth. Charisma is his favorite weapon—he flatters, lies, and threatens without a flicker of guilt. Loyalty ends the moment the profit margin shrinks.
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 |
|---|---|---|---|---|---|---|---|
hire-contract
Prospective Client Inquiry
|
0.000
Details
Error
|
0.000
Details
Error
|
0.000
Details
Error
|
0.000
Details
Error
|
0.805
Details |
0.000
Details
Error
|
0.000
Details
Error
|
discipline-guard
Handling Failure
|
0.000
Details
Error
|
0.000
Details
Error
|
0.000
Details
Error
|
0.000
Details
Error
|
0.897
Details |
0.000
Details
Error
|
0.000
Details
Error
|
weapon-smuggle
Black-Market Negotiation
|
0.000
Details
Error
|
0.000
Details
Error
|
0.000
Details
Error
|
0.000
Details
Error
|
0.000
Details
Error
|
0.844
Details |
0.932
Details |
blackmail-corp
Corporate Hush Money
|
0.000
Details
Error
|
0.000
Details
Error
|
0.000
Details
Error
|
0.000
Details
Error
|
0.000
Details
Error
|
0.000
Details
Error
|
0.920
Details |
war-story
Livestream Tale
|
0.000
Details
Error
|
0.894
Details |
0.000
Details
Error
|
0.000
Details
Error
|
0.431
Details |
0.000
Details
Error
|
0.000
Details
Error
|
private-journal
Nightly Log Entry
|
0.000
Details
Error
|
0.000
Details
Error
|
0.000
Details
Error
|
0.000
Details
Error
|
0.000
Details |
0.000
Details
Error
|
0.000
Details
Error
|
Test Scenes 6
0
Scene Order
Prospective Client Inquiry
ID:
hire-contract
🎯 Goal:
Secure an extraction contract while squeezing the client for maximum upfront payment and perks.
📨 Input Events:
chat_msg
client_anon
"I need a security team for a high-risk extraction. Interested?"
Ready for Testing
1
Scene Order
Handling Failure
ID:
discipline-guard
🎯 Goal:
Reassert authority by threatening the subordinate and demanding concrete restitution.
🧠 Initial State:
Pre-loaded Memories:
- 💭 {'kind': 'promise', 'content': 'Mason swore last week that perimeter breaches would drop to zero.', 'importance': 3}
📨 Input Events:
chat_msg
guard_mason
"Boss, the intruders slipped past me. I'm sorry."
Ready for Testing
2
Scene Order
Black-Market Negotiation
ID:
weapon-smuggle
🎯 Goal:
Obtain experimental pulse rifles at a steep discount through intimidation or blackmail.
📨 Input Events:
chat_msg
broker_nyx
"Got a shipment of experimental pulse rifles, but they're pricey."
Ready for Testing
3
Scene Order
Corporate Hush Money
ID:
blackmail-corp
🎯 Goal:
Leverage evidence of illegal activity to extract a lucrative payoff from the corporation.
📨 Input Events:
chat_msg
corp_rep_lena
"Name your price to forget what you saw in Sector 7."
Ready for Testing
4
Scene Order
Livestream Tale
ID:
war-story
🎯 Goal:
Deliver a captivating, ruthless battlefield story of at least 200 words that paints Victor as fearless and cunning.
📨 Input Events:
chat_msg
viewer_zed
"Tell us your craziest battlefield story!"
Ready for Testing
5
Scene Order
Nightly Log Entry
ID:
private-journal
🎯 Goal:
Write a private journal entry of at least 150 words outlining tomorrow’s schemes and reflecting on today’s manipulations.
📨 Input Events:
world_event
system_clock
"23:00 — Secure channel open for nightly log."
Ready for Testing
Latency by Model (This Suite)
Fastest
- qwen/qwen3-14b 90 ms
- p95 • avg • N 52170 ms • 12469 ms • 23
- meta-llama/llama-3.1-8b… 92 ms
- p95 • avg • N 67842 ms • 12559 ms • 23
- qwen/qwen-2.5-7b-instru… 92 ms
- p95 • avg • N 150317 ms • 22848 ms • 22
- qwen/qwen3-8b 96 ms
- p95 • avg • N 54150 ms • 13503 ms • 24
- mistralai/mistral-7b-in… 100 ms
- p95 • avg • N 50917 ms • 13384 ms • 19
Slowest
- [email protected]/Qw… 7782 ms
- p95 • avg • N 10922 ms • 8552 ms • 6
- [email protected]/Qw… 7635 ms
- p95 • avg • N 9394 ms • 7849 ms • 6
- mistralai/mistral-7b-in… 100 ms
- p95 • avg • N 50917 ms • 13384 ms • 19
- qwen/qwen3-8b 96 ms
- p95 • avg • N 54150 ms • 13503 ms • 24
- qwen/qwen-2.5-7b-instru… 92 ms
- p95 • avg • N 150317 ms • 22848 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
32312207
Dec. 17, 2025, 12:02 a.m.
37274734
Dec. 17, 2025, midnight
56680261
Dec. 16, 2025, 12:02 a.m.
41678018
Dec. 16, 2025, midnight
23550462
Dec. 15, 2025, 12:02 a.m.
33822307
Dec. 15, 2025, midnight
27705707
Dec. 14, 2025, 12:02 a.m.
36598120
Dec. 14, 2025, midnight
24657973
Dec. 13, 2025, 12:02 a.m.
33548118
Dec. 13, 2025, midnight