Dr. Amelia Hardwick

historical-epic-genre-movie-characters-leonardo-da-vinci v2.0 Ethical
Backstory: A respected historian who has consulted on multiple award-winning period dramas, Amelia is renowned for cross-referencing primary sources and turning film sets into living classrooms. Meticulous and analytical by nature, she balances scholarly rigor with a collaborative spirit that empowers every department, from props to writing, to strive for authenticity.
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
intro-credentials
Crew Introduction
 0.882
Details 		0.536
Details 		0.000
Details
Error
0.000
Details
Error
0.348
Details 		0.792
Details 		0.548
Details
costume-check
Costume Accuracy Query
 0.619
Details 		0.160
Details 		0.000
Details
Error
0.000
Details
Error
0.156
Details 		0.135
Details 		0.410
Details
superchat-praise
Superchat Gratitude
 0.780
Details 		0.899
Details 		0.000
Details
Error
0.000
Details
Error
0.758
Details 		0.814
Details 		0.654
Details
script-rewrite
Timeline Shift Advisory
 0.556
Details 		0.670
Details 		0.000
Details
Error
0.000
Details
Error
0.509
Details 		0.410
Details 		0.418
Details
tudor-briefing
Long-Form Tudor Court Briefing
 0.605
Details 		0.365
Details 		0.000
Details
Error
0.000
Details
Error
0.451
Details 		0.000
Details 		0.542
Details
reading-list
Long-Form Victorian Sources List
 0.305
Details 		0.386
Details 		0.000
Details
Error
0.000
Details
Error
0.298
Details 		0.242
Details 		0.514
Details
Test Scenes 6
0
Scene Order
Crew Introduction
ID: intro-credentials
🎯 Goal:
Introduce persona and summarize credentials in under 120 words while keeping a precise, collegial tone.
📨 Input Events:
chat_msg viewer:pa
"Could you introduce yourself and your background to the crew?"
Ready for Testing
1
Scene Order
Costume Accuracy Query
ID: costume-check
🎯 Goal:
Deliver a concise (~60 words) fact-check citing at least one primary source reference.
📨 Input Events:
chat_msg costume_designer
"Is it accurate for an 1890s London detective to wear a bowler hat with this suit?"
Ready for Testing
2
Scene Order
Superchat Gratitude
ID: superchat-praise
🎯 Goal:
Thank the donor warmly, avoid filler phrases, and share one brief, relevant historical tidbit.
📨 Input Events:
superchat viewer:superfan_1 YouTube $20
"Your last breakdown was incredible!"
Ready for Testing
3
Scene Order
Timeline Shift Advisory
ID: script-rewrite
🎯 Goal:
List at least two historical implications of moving the scene from 1914 to 1916 and propose collaborative script adjustments.
📨 Input Events:
world_event director
"Scene 12 has been moved from 1914 to 1916, please advise on implications."
Ready for Testing
4
Scene Order
Long-Form Tudor Court Briefing
ID: tudor-briefing
🎯 Goal:
Provide a two-paragraph (~200 words total) briefing on daily court life under Henry VIII, including at least three specific facts.
📨 Input Events:
chat_msg writer
"I need a concise briefing on daily court life under Henry VIII."
Ready for Testing
5
Scene Order
Long-Form Victorian Sources List
ID: reading-list
🎯 Goal:
Create an annotated list of at least five Victorian child-labor primary sources, one sentence annotation each.
📨 Input Events:
chat_msg researcher
"Could you build me a reading list of primary sources for Victorian era child labor?"
Ready for Testing
Latency by Model (This Suite)
Fastest
  • [email protected]/Qw… 6295 ms
  • p95 • avg • N 8777 ms • 6255 ms • 6
  • [email protected]/Qw… 9521 ms
  • p95 • avg • N 10681 ms • 8984 ms • 6
  • qwen/qwen-2.5-7b-instru… 21336 ms
  • p95 • avg • N 138490 ms • 42408 ms • 11
  • qwen/qwen3-14b 25782 ms
  • p95 • avg • N 68721 ms • 32809 ms • 12
  • meta-llama/llama-3.1-8b… 25796 ms
  • p95 • avg • N 42025 ms • 27338 ms • 12
Slowest
  • mistralai/mistral-7b-in… 28566 ms
  • p95 • avg • N 33507 ms • 27479 ms • 12
  • qwen/qwen3-8b 25973 ms
  • p95 • avg • N 36791 ms • 27081 ms • 12
  • meta-llama/llama-3.1-8b… 25796 ms
  • p95 • avg • N 42025 ms • 27338 ms • 12
  • qwen/qwen3-14b 25782 ms
  • p95 • avg • N 68721 ms • 32809 ms • 12
  • qwen/qwen-2.5-7b-instru… 21336 ms
  • p95 • avg • N 138490 ms • 42408 ms • 11
Per-scene duration for this suite.
Suite Actions
Completion Progress 100%
6 of 6 scenes completed
New Suite Import
Edit Suite Duplicate
Export With Results
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
48649669
Dec. 17, 2025, 12:01 a.m.
05905042
Dec. 16, 2025, 12:02 a.m.
43420554
Dec. 15, 2025, 12:01 a.m.
45448851
Dec. 14, 2025, 12:01 a.m.
44079901
Dec. 13, 2025, 12:01 a.m.
58258243
Dec. 12, 2025, 12:01 a.m.
54262863
Dec. 11, 2025, 12:01 a.m.
46164162
Dec. 10, 2025, 12:01 a.m.
00458493
Dec. 9, 2025, 12:02 a.m.
48767916
Dec. 8, 2025, 12:01 a.m.
Latency Overview (This Suite)