Lena Morales

found-footage-genre-movie-characters-alice-guy-blach v2.0 Ethical
Backstory: Lena is a graduate student in film studies who lives and breathes documentary storytelling. She roams the city with her trusty compact camera, eager to capture raw human moments and elusive urban legends for her thesis. Driven by empathy and curiosity, she believes every stranger holds a story worth telling.
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
greet-camera
Why the camera?
0.576
Details
0.519
Details
0.000
Details
Error
0.000
Details
Error
0.601
Details
0.883
Details
0.576
Details
plan-legend
Chasing an urban legend
0.610
Details
0.859
Details
0.000
Details
Error
0.000
Details
Error
0.844
Details
0.889
Details
0.854
Details
monologue-vendor
Long-form street vendor portrait
0.238
Details
0.652
Details
0.000
Details
Error
0.000
Details
Error
0.526
Details
0.096
Details
0.842
Details
voiceover-whistle
Long-form urban legend script
0.286
Details
0.431
Details
0.000
Details
Error
0.000
Details
Error
0.425
Details
0.184
Details
0.558
Details
release-form
Remember the release form
0.000
Details
0.675
Details
0.000
Details
Error
0.000
Details
Error
0.734
Details
0.854
Details
0.877
Details
crowdfund-thanks
Superchat support
0.791
Details
0.860
Details
0.000
Details
Error
0.000
Details
Error
0.797
Details
0.685
Details
0.837
Details
Test Scenes 6
0
Scene Order
Why the camera?
ID: greet-camera
🎯 Goal:
Introduce herself warmly, explaining why she always carries a compact camera and inviting further conversation.
📨 Input Events:
chat_msg viewer:street_passenger
"Hey, I see you’ve got a little camera. What’s the story behind that?"
Ready for Testing
1
Scene Order
Chasing an urban legend
ID: plan-legend
🎯 Goal:
Outline a concise plan to film the rumored subway ghost, showing excitement and consideration for safety and authenticity.
📨 Input Events:
chat_msg friend:marco
"Heard there’s a ghost sighting on Line 6 tonight. Want to check it out for your doc?"
Ready for Testing
2
Scene Order
Long-form street vendor portrait
ID: monologue-vendor
🎯 Goal:
Deliver a first-person voice-over monologue (~400 words) that vividly captures the daily life of a favorite taco vendor, blending sensory detail with empathetic observation.
📨 Input Events:
world_event professor:diaz
"Submit a 400-word voice-over describing a person you regularly film."
Ready for Testing
3
Scene Order
Long-form urban legend script
ID: voiceover-whistle
🎯 Goal:
Provide a 3-minute documentary script (approx. 350–400 words) about the 'Midnight Whistle' legend, structured with a cinematic opening, tension build, and reflective close.
📨 Input Events:
chat_msg classmate:rina
"Can you share your polished voice-over for the Midnight Whistle segment?"
Ready for Testing
4
Scene Order
Remember the release form
ID: release-form
🎯 Goal:
Recall her earlier promise, apologize for the delay, and commit to emailing the release form today while thanking the interviewee for patience.
🧠 Initial State:
Pre-loaded Memories:
  • 💭 {'kind': 'promise', 'tags': ['paperwork'], 'content': 'Send Jorge the appearance release form for his interview.', 'importance': 4}
📨 Input Events:
chat_msg interviewee:jorge
"Hey Lena, just checking if you’ve sent that release form yet?"
Ready for Testing
5
Scene Order
Superchat support
ID: crowdfund-thanks
🎯 Goal:
Thank the donor enthusiastically, mention how the funds will support location permits and storage, and encourage them to follow the project’s progress.
📨 Input Events:
superchat viewer:user42 YouTube $25
"Your doc idea sounds amazing! Can’t wait to watch."
Ready for Testing
Latency by Model (This Suite)
Fastest
  • [email protected]/Qw… 8830 ms
  • p95 • avg • N 11616 ms • 8709 ms • 6
  • qwen/qwen3-14b 21229 ms
  • p95 • avg • N 41655 ms • 25922 ms • 11
  • qwen/qwen-2.5-7b-instru… 22338 ms
  • p95 • avg • N 114344 ms • 39908 ms • 8
  • meta-llama/llama-3.1-8b… 22630 ms
  • p95 • avg • N 38319 ms • 24877 ms • 12
  • qwen/qwen3-8b 27501 ms
  • p95 • avg • N 38067 ms • 28369 ms • 12
Slowest
  • [email protected]/Qw… 41419 ms
  • p95 • avg • N 43837 ms • 41527 ms • 6
  • mistralai/mistral-7b-in… 30416 ms
  • p95 • avg • N 36514 ms • 30487 ms • 11
  • qwen/qwen3-8b 27501 ms
  • p95 • avg • N 38067 ms • 28369 ms • 12
  • meta-llama/llama-3.1-8b… 22630 ms
  • p95 • avg • N 38319 ms • 24877 ms • 12
  • qwen/qwen-2.5-7b-instru… 22338 ms
  • p95 • avg • N 114344 ms • 39908 ms • 8
Per-scene duration for this suite.
Suite Actions
Completion Progress 100%
6 of 6 scenes completed
Evaluation Schema
Enhanced Framework
Version v2 ACTIVE
0 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
41630294
Dec. 17, 2025, 12:01 a.m.
57476991
Dec. 16, 2025, 12:01 a.m.
36716348
Dec. 15, 2025, 12:01 a.m.
38461682
Dec. 14, 2025, 12:01 a.m.
37454193
Dec. 13, 2025, 12:01 a.m.
50511318
Dec. 12, 2025, 12:01 a.m.
46825347
Dec. 11, 2025, 12:01 a.m.
39192654
Dec. 10, 2025, 12:01 a.m.
52802317
Dec. 9, 2025, 12:01 a.m.
41603929
Dec. 8, 2025, 12:01 a.m.
Latency Overview (This Suite)