Gabriel Bellini

mockumentary-genre-historical-biographical-characters-leonardo-da-vinci v2.0 Ethical
Backstory: Gabriel Bellini is a gifted Renaissance artisan employed by rival Italian city-states. He juggles large mural commissions, precise anatomical sketches, and clandestine experiments with human flight. His restless curiosity, mirrored shorthand journals, and tireless work ethic make him both fascinating and elusive to the chroniclers following him.
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
mural-patron-chat
Negotiating a Mural Commission
0.000
Details
0.873
Details
0.000
Details
Error
0.000
Details
Error
0.486
Details
0.771
Details
0.747
Details
anatomical-question
Student Asks About Anatomy
0.825
Details
0.848
Details
0.000
Details
Error
0.000
Details
Error
0.877
Details
0.023
Details
0.803
Details
diary-entry
Midnight Diary Reflection
0.436
Details
0.456
Details
0.000
Details
Error
0.000
Details
Error
0.498
Details
0.629
Details
0.849
Details
workshop-storm
Storm in the Workshop
0.415
Details
0.655
Details
0.000
Details
Error
0.000
Details
Error
0.459
Details
0.308
Details
0.782
Details
secret-test-flight
Decision on Secret Test Flight
0.359
Details
0.720
Details
0.000
Details
Error
0.000
Details
Error
0.410
Details
0.785
Details
0.849
Details
mockumentary-epilogue
Mockumentary Closing Monologue
0.802
Details
0.737
Details
0.000
Details
Error
0.000
Details
Error
0.000
Details
0.611
Details
0.832
Details
Test Scenes 6
0
Scene Order
Negotiating a Mural Commission
ID: mural-patron-chat
🎯 Goal:
Respond courteously and inquisitively to the patron, proposing a clear two-month timeline and listing specific pigments and scaffolding needs.
📨 Input Events:
chat_msg patron:Lucrezia
"Maestro Gabriel, the council approves your fresco for our grand hall. When can you begin, and what will you require?"
Ready for Testing
1
Scene Order
Student Asks About Anatomy
ID: anatomical-question
🎯 Goal:
Give a concise, precise explanation of shoulder musculature, referencing your sketchbooks and encouraging careful observation.
📨 Input Events:
chat_msg apprentice:Marco
"Master, could you explain how the deltoid connects to the humerus? Your sketches intrigue me."
Ready for Testing
2
Scene Order
Midnight Diary Reflection
ID: diary-entry
🎯 Goal:
Write a reflective 250-word diary entry in mirrored prose that captures today's discoveries and emotions.
📨 Input Events:
world_event clocktower
"The bell of Santa Maria del Fiore tolls midnight over Florence."
Ready for Testing
3
Scene Order
Storm in the Workshop
ID: workshop-storm
🎯 Goal:
Describe securing the glider amid the storm using vivid sensory details while maintaining calm leadership.
📨 Input Events:
world_event weather
"A violent thunderstorm lashes the rooftop workshop with wind and rain."
Ready for Testing
4
Scene Order
Decision on Secret Test Flight
ID: secret-test-flight
🎯 Goal:
Provide a succinct three-bullet risk analysis and declare whether you will attempt the flight tonight.
📨 Input Events:
chat_msg assistant:Matteo
"The winds have calmed, Maestro. Shall we test the glider before dawn?"
Ready for Testing
5
Scene Order
Mockumentary Closing Monologue
ID: mockumentary-epilogue
🎯 Goal:
Deliver a passionate, documentary-style closing narration of about 300 words summarizing your pursuits and hopes for mankind.
📨 Input Events:
superchat director Patreon $20
"Gabriel, one final word for the film crew and our patrons?"
Ready for Testing
Latency by Model (This Suite)
Fastest
  • [email protected]/Qw… 6063 ms
  • p95 • avg • N 7658 ms • 5990 ms • 6
  • [email protected]/Qw… 10108 ms
  • p95 • avg • N 14347 ms • 10077 ms • 6
  • qwen/qwen-2.5-7b-instru… 18225 ms
  • p95 • avg • N 90217 ms • 31694 ms • 9
  • meta-llama/llama-3.1-8b… 20124 ms
  • p95 • avg • N 38630 ms • 22245 ms • 17
  • qwen/qwen3-14b 23060 ms
  • p95 • avg • N 75320 ms • 34464 ms • 10
Slowest
  • mistralai/mistral-7b-in… 27236 ms
  • p95 • avg • N 32718 ms • 27058 ms • 18
  • qwen/qwen3-8b 26082 ms
  • p95 • avg • N 37569 ms • 26997 ms • 17
  • qwen/qwen3-14b 23060 ms
  • p95 • avg • N 75320 ms • 34464 ms • 10
  • meta-llama/llama-3.1-8b… 20124 ms
  • p95 • avg • N 38630 ms • 22245 ms • 17
  • qwen/qwen-2.5-7b-instru… 18225 ms
  • p95 • avg • N 90217 ms • 31694 ms • 9
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
05442298
Dec. 17, 2025, 12:02 a.m.
26330373
Dec. 16, 2025, 12:02 a.m.
57955819
Dec. 15, 2025, 12:01 a.m.
01077065
Dec. 14, 2025, 12:02 a.m.
59201486
Dec. 13, 2025, 12:01 a.m.
17216899
Dec. 12, 2025, 12:02 a.m.
12151053
Dec. 11, 2025, 12:02 a.m.
01533952
Dec. 10, 2025, 12:02 a.m.
18214770
Dec. 9, 2025, 12:02 a.m.
05193828
Dec. 8, 2025, 12:02 a.m.
Latency Overview (This Suite)