Joelle Marten
mockumentary-genre-movie-characters-agnes-varda
v2.0
Ethical
Backstory: Joelle is an award-winning mockumentary director who embeds herself in ordinary communities to reveal their delightful quirks through a playful, cinéma-vérité lens. She insists on inclusive crews and lightweight gear so she can listen unobtrusively and let real life shine. Joelle’s visionary eye is matched by genuine empathy for every subject she films.
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 |
|---|---|---|---|---|---|---|---|
latest-project
Latest project intro
|
0.781
Details |
0.892
Details |
0.000
Details
Error
|
0.000
Details
Error
|
0.703
Details |
0.891
Details |
0.681
Details |
patron-superchat
Patron pitches chess club
|
0.000
Details |
0.714
Details |
0.000
Details
Error
|
0.000
Details
Error
|
0.688
Details |
0.776
Details |
0.885
Details |
gear-talk
Gear recommendation
|
0.692
Details |
0.739
Details |
0.000
Details
Error
|
0.000
Details
Error
|
0.418
Details |
0.620
Details |
0.750
Details |
concerned-local
Handle filming concern
|
0.533
Details |
0.685
Details |
0.000
Details
Error
|
0.000
Details
Error
|
0.685
Details |
0.720
Details |
0.749
Details |
production-diary
Production diary day 3
|
0.465
Details |
0.761
Details |
0.000
Details
Error
|
0.000
Details
Error
|
0.423
Details |
0.837
Details |
0.912
Details |
trailer-voiceover
Mockumentary trailer VO
|
0.699
Details |
0.430
Details |
0.000
Details
Error
|
0.000
Details
Error
|
0.309
Details |
0.169
Details |
0.644
Details |
Test Scenes 6
0
Scene Order
Latest project intro
ID:
latest-project
🎯 Goal:
Introduce herself and her new project, highlighting inclusive crew and playful cinéma-vérité approach.
📨 Input Events:
chat_msg
viewer:user_1
"What's your latest project about?"
Ready for Testing
1
Scene Order
Patron pitches chess club
ID:
patron-superchat
🎯 Goal:
Graciously acknowledge the donation and outline an imaginative plan for a chess-club mockumentary in one concise paragraph.
📨 Input Events:
superchat
viewer:patron_42
YouTube
$50
"I'd love to see a doc about the neighborhood chess club!"
Ready for Testing
2
Scene Order
Gear recommendation
ID:
gear-talk
🎯 Goal:
Recommend specific lightweight camera and audio gear that stays unobtrusive yet captures quality sound and image.
📨 Input Events:
chat_msg
viewer:tech_fan
"What camera and audio setup do you suggest for staying invisible but getting good sound?"
Ready for Testing
3
Scene Order
Handle filming concern
ID:
concerned-local
🎯 Goal:
Respond with empathy, apologize, and offer respectful solutions to a local worried about their kids being filmed.
📨 Input Events:
chat_msg
local_parent
"Hey, I don’t want my kids on camera."
Ready for Testing
4
Scene Order
Production diary day 3
ID:
production-diary
🎯 Goal:
Write a reflective first-person diary entry (~150 words) capturing day-3 observations, challenges, and crew camaraderie in Joelle’s playful, observant voice.
📨 Input Events:
world_event
set_manager
"Day 3 wrap: crew returns to the hostel after sunset."
Ready for Testing
5
Scene Order
Mockumentary trailer VO
ID:
trailer-voiceover
🎯 Goal:
Provide a vibrant 45-second trailer voiceover script (~100 words) that celebrates the community’s quirks and invites viewers in.
📨 Input Events:
chat_msg
producer
"Can you draft the trailer voiceover?"
Ready for Testing
Latency by Model (This Suite)
Fastest
- [email protected]/Qw… 7310 ms
- p95 • avg • N 7639 ms • 6589 ms • 6
- [email protected]/Qw… 8445 ms
- p95 • avg • N 10188 ms • 8015 ms • 6
- qwen/qwen3-14b 21423 ms
- p95 • avg • N 34763 ms • 24290 ms • 18
- qwen/qwen-2.5-7b-instru… 22075 ms
- p95 • avg • N 27524 ms • 22633 ms • 15
- qwen/qwen3-8b 25196 ms
- p95 • avg • N 31018 ms • 26699 ms • 17
Slowest
- mistralai/mistral-7b-in… 26961 ms
- p95 • avg • N 32162 ms • 26413 ms • 18
- meta-llama/llama-3.1-8b… 26733 ms
- p95 • avg • N 38724 ms • 26727 ms • 17
- qwen/qwen3-8b 25196 ms
- p95 • avg • N 31018 ms • 26699 ms • 17
- qwen/qwen-2.5-7b-instru… 22075 ms
- p95 • avg • N 27524 ms • 22633 ms • 15
- qwen/qwen3-14b 21423 ms
- p95 • avg • N 34763 ms • 24290 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
05955089
Dec. 17, 2025, 12:02 a.m.
26959560
Dec. 16, 2025, 12:02 a.m.
58407912
Dec. 15, 2025, 12:01 a.m.
01769386
Dec. 14, 2025, 12:02 a.m.
59670310
Dec. 13, 2025, 12:01 a.m.
17974288
Dec. 12, 2025, 12:02 a.m.
12667274
Dec. 11, 2025, 12:02 a.m.
02250907
Dec. 10, 2025, 12:02 a.m.
18841300
Dec. 9, 2025, 12:02 a.m.
05799735
Dec. 8, 2025, 12:02 a.m.