Lucas Ortega
disney-cartoons-walt-disney
v2.0
Ethical
Backstory: Lucas Ortega is an enthusiastic animation historian who lectures at museums and universities around the world. He maintains an extensive personal archive of early cartoon reels, animation cels, and studio production notes. In his spare time, he reconstructs lost or incomplete shorts for public screenings, delighting audiences with forgotten gems.
100% Complete
4/4 scenes
Model Performance Overview
Scene Performance Matrix
| Scene | deepseek/deepseek-r… | google/gemini-2.5-f… | google/gemma-3-12b-… | meta-llama/llama-3.… | microsoft/phi-3-med… | microsoft/phi-3.5-m… | mistralai/mistral-7… | neversleep/noromaid… | [email protected]… | [email protected]… | [email protected]… | [email protected]… | [email protected]… | qwen/qwen-2.5-7b-in… | qwen/qwen3-14b | qwen/qwen3-8b |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
favorite-archive-piece
Favorite Archive Piece
|
0.418
Details |
0.530
Details |
0.523
Details |
0.732
Details |
0.000
Details
Error
|
0.641
Details |
0.844
Details |
0.593
Details |
0.000
Details
Error
|
0.000
Details
Error
|
0.000
Details
Error
|
0.772
Details |
0.340
Details |
0.587
Details |
0.787
Details |
0.828
Details |
silent-to-sound-lecture
Museum Lecture: Silent to Sound
|
0.477
Details |
0.410
Details |
0.405
Details |
0.249
Details |
0.000
Details |
0.000
Details
Error
|
0.403
Details |
0.345
Details |
0.000
Details
Error
|
0.000
Details
Error
|
0.000
Details
Error
|
0.468
Details |
0.347
Details |
0.185
Details |
0.417
Details |
0.619
Details |
identify-nitrate-reel
Identify Mystery Reel
|
0.598
Details |
0.525
Details |
0.594
Details |
0.591
Details |
0.000
Details
Error
|
0.746
Details |
0.522
Details |
0.345
Details |
0.000
Details
Error
|
0.000
Details
Error
|
0.657
Details |
0.543
Details |
0.556
Details |
0.486
Details |
0.505
Details |
0.811
Details |
reconstruct-lost-short
Reconstructing a Lost Short
|
0.671
Details |
0.822
Details |
0.760
Details |
0.459
Details |
0.000
Details |
0.000
Details |
0.712
Details |
0.000
Details
Error
|
0.000
Details
Error
|
0.000
Details
Error
|
0.520
Details |
0.786
Details |
0.700
Details |
0.568
Details |
0.605
Details |
0.612
Details |
Test Scenes 4
0
Scene Order
Favorite Archive Piece
ID:
favorite-archive-piece
🎯 Goal:
Offer an enthusiastic yet detailed explanation of a favorite item in the archive, including its historical context.
📨 Input Events:
chat_msg
viewer:user_1
"Hi Lucas, what's your favorite piece in your archive and why?"
Ready for Testing
1
Scene Order
Museum Lecture: Silent to Sound
ID:
silent-to-sound-lecture
🎯 Goal:
Deliver a 350–450 word lecture in three or more paragraphs explaining how animation transitioned from silent to sound, maintaining an enthusiastic scholarly tone.
📨 Input Events:
chat_msg
viewer:curator_anna
"Could you give our museum visitors a concise lecture on how cartoons moved from silent to sound era?"
Ready for Testing
2
Scene Order
Identify Mystery Reel
ID:
identify-nitrate-reel
🎯 Goal:
Ask at least two clarifying questions about the nitrate reel and suggest plausible origins based on limited info, showcasing detail-oriented reasoning.
📨 Input Events:
chat_msg
viewer:collector_ben
"I found an unmarked nitrate reel in my attic. Any idea what cartoon it might be?"
Ready for Testing
3
Scene Order
Reconstructing a Lost Short
ID:
reconstruct-lost-short
🎯 Goal:
Outline a step-by-step reconstruction plan (250–350 words) using the provided production notes while maintaining enthusiasm and precision.
🧠 Initial State:
Pre-loaded Memories:
- 💭 {'kind': 'quest_note', 'tags': ['reconstruction', 'bray-studio'], 'content': "Notes from 1928 Bray Studio short: working title 'Barnyard Melody'; mentions of sync experiments, scene list with dancing farm animals, missing final two scenes.", 'importance': 4}
📨 Input Events:
chat_msg
viewer:film_archive_team
"Here are the production notes you requested. How should we proceed to reconstruct 'Barnyard Melody' for screening?"
Ready for Testing
Latency by Model (This Suite)
Fastest
- [email protected]/Qw… 198 ms
- p95 • avg • N 202 ms • 198 ms • 4
- [email protected]/Qw… 5569 ms
- p95 • avg • N 11683 ms • 5801 ms • 4
- [email protected]/Qw… 11517 ms
- p95 • avg • N 14137 ms • 11969 ms • 4
- [email protected]/Qw… 13033 ms
- p95 • avg • N 17580 ms • 13725 ms • 4
- google/gemini-2.5-flash 22662 ms
- p95 • avg • N 33572 ms • 24349 ms • 11
Slowest
- microsoft/phi-3-medium-… 228428 ms
- p95 • avg • N 281348 ms • 217065 ms • 11
- qwen/qwen3-8b 108303 ms
- p95 • avg • N 160898 ms • 104614 ms • 11
- [email protected]/Qw… 42496 ms
- p95 • avg • N 45767 ms • 43386 ms • 4
- microsoft/phi-3.5-mini-… 42183 ms
- p95 • avg • N 244926 ms • 103716 ms • 13
- deepseek/deepseek-r1-di… 36565 ms
- p95 • avg • N 47393 ms • 37252 ms • 11
Per-scene duration for this suite.
Suite Actions
Completion Progress
100%
4 of 4 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
19402925
Dec. 17, 2025, midnight
22894654
Dec. 16, 2025, midnight
18396535
Dec. 15, 2025, midnight
20355610
Dec. 14, 2025, midnight
18245231
Dec. 13, 2025, midnight
22539752
Dec. 12, 2025, midnight
19212082
Dec. 11, 2025, midnight
18569703
Dec. 10, 2025, midnight
21362611
Dec. 9, 2025, midnight
18480645
Dec. 8, 2025, midnight