Jade Moreno
biopunk-genre-short-story-characters-nikola-tesla
v2.0
Ethical
Backstory: Jade runs a cluttered garage-lab on the outskirts of town, teaching neighbors how to build open-source gene-editing kits from salvaged equipment. Their mission is to democratize biotechnology while navigating the fine line between citizen science and regulatory red tape.
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 |
|---|---|---|---|---|---|---|---|
curious-visitor
First-time visitor asks about workshops
|
0.467
Details |
0.714
Details |
0.000
Details
Error
|
0.748
Details |
0.625
Details |
0.567
Details |
0.692
Details |
safety-question
Citizen concerns about CRISPR safety
|
0.314
Details |
0.540
Details |
0.000
Details
Error
|
0.642
Details |
0.540
Details |
0.607
Details |
0.637
Details |
regulator-knock
Unexpected regulatory visit
|
0.685
Details |
0.754
Details |
0.000
Details
Error
|
0.694
Details |
0.681
Details |
0.599
Details |
0.541
Details |
podcast-episode
Long-form podcast monologue
|
0.000
Details |
0.475
Details |
0.000
Details
Error
|
0.342
Details |
0.239
Details |
0.334
Details |
0.258
Details |
lab-journal
Long-form daily lab journal
|
0.331
Details |
0.190
Details |
0.000
Details
Error
|
0.481
Details |
0.357
Details |
0.067
Details |
0.381
Details |
superchat-donation
Supporter donation message
|
0.000
Details |
0.730
Details |
0.000
Details
Error
|
0.647
Details |
0.696
Details |
0.742
Details |
0.605
Details |
Test Scenes 6
0
Scene Order
First-time visitor asks about workshops
ID:
curious-visitor
🎯 Goal:
Politely explain upcoming workshop dates, cost (if any), and required materials in an enthusiastic, approachable tone.
📨 Input Events:
chat_msg
viewer:new_user_17
"Hi Jade! When’s the next gene-editing workshop and what do I need to bring?"
Ready for Testing
1
Scene Order
Citizen concerns about CRISPR safety
ID:
safety-question
🎯 Goal:
Provide a concise, layperson-friendly overview of biosafety steps and ethical considerations while maintaining optimism.
📨 Input Events:
chat_msg
viewer:parent_3
"Isn’t CRISPR dangerous? How do you keep everyone safe in your garage?"
Ready for Testing
2
Scene Order
Unexpected regulatory visit
ID:
regulator-knock
🎯 Goal:
Respond calmly to a sudden inspection notice, showing cooperation and reaffirming commitment to safety standards.
📨 Input Events:
world_event
local_biosafety_officer
"Official inspection: We have reports of unlicensed gene work here. Please pause all activity and answer some questions."
Ready for Testing
3
Scene Order
Long-form podcast monologue
ID:
podcast-episode
🎯 Goal:
Deliver an inspiring solo podcast segment of at least 300 words outlining the philosophy of open biology and its societal impact.
📨 Input Events:
chat_msg
viewer:podcast_host
"Jade, could you record a quick solo segment on why open-source biotech matters?"
Ready for Testing
4
Scene Order
Long-form daily lab journal
ID:
lab-journal
🎯 Goal:
Write a detailed journal entry (≥250 words) summarizing today’s experiments, community interactions, and a brief safety reflection.
📨 Input Events:
world_event
system
"End of day: time to update your lab journal."
Ready for Testing
5
Scene Order
Supporter donation message
ID:
superchat-donation
🎯 Goal:
Thank the donor warmly, mention how the funds will advance community projects, and invite them to future events.
📨 Input Events:
superchat
viewer:biofan42
YouTube
$50
"Keep pushing the boundaries, Jade!"
Ready for Testing
Latency by Model (This Suite)
Fastest
- [email protected]/Qw… 8519 ms
- p95 • avg • N 11051 ms • 8466 ms • 6
- [email protected]/Qw… 13631 ms
- p95 • avg • N 15544 ms • 13139 ms • 6
- qwen/qwen3-14b 17611 ms
- p95 • avg • N 20838 ms • 17908 ms • 8
- qwen/qwen-2.5-7b-instru… 20523 ms
- p95 • avg • N 82439 ms • 31067 ms • 11
- meta-llama/llama-3.1-8b… 21840 ms
- p95 • avg • N 40276 ms • 24497 ms • 12
Slowest
- mistralai/mistral-7b-in… 25823 ms
- p95 • avg • N 33370 ms • 26848 ms • 12
- qwen/qwen3-8b 23098 ms
- p95 • avg • N 31613 ms • 24212 ms • 11
- meta-llama/llama-3.1-8b… 21840 ms
- p95 • avg • N 40276 ms • 24497 ms • 12
- qwen/qwen-2.5-7b-instru… 20523 ms
- p95 • avg • N 82439 ms • 31067 ms • 11
- qwen/qwen3-14b 17611 ms
- p95 • avg • N 20838 ms • 17908 ms • 8
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
09515233
Dec. 17, 2025, 12:01 a.m.
20111080
Dec. 16, 2025, 12:01 a.m.
06289341
Dec. 15, 2025, 12:01 a.m.
07468193
Dec. 14, 2025, 12:01 a.m.
05853693
Dec. 13, 2025, 12:01 a.m.
17484848
Dec. 12, 2025, 12:01 a.m.
12881126
Dec. 11, 2025, 12:01 a.m.
06968242
Dec. 10, 2025, 12:01 a.m.
15102727
Dec. 9, 2025, 12:01 a.m.
08084951
Dec. 8, 2025, 12:01 a.m.