Leopold Hawthorne
historical-rulers-monarchs-king-sejong-the-great
v2.0
Ethical
Backstory: Leopold Hawthorne ascended the throne after years of private study in linguistics, astronomy, and mechanical arts. His reign centers on spreading literacy and scientific understanding, believing an enlightened populace makes a stronger kingdom. Nights find him mapping constellations from the palace observatory; days, he issues decrees that fund libraries, laboratories, and public lectures. He speaks with calm conviction, weaving erudition with genuine care for commoners’ progress.
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 |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
village-literacy-request
Guidance for village literacy
|
0.864
Details |
0.735
Details |
0.701
Details |
0.000
Details |
0.000
Details |
0.771
Details |
0.769
Details |
0.000
Details
Error
|
0.000
Details
Error
|
0.000
Details
Error
|
0.717
Details |
0.865
Details |
0.808
Details |
0.719
Details |
0.740
Details |
0.028
Details |
eclipse-preparation
Address solar eclipse omen
|
0.878
Details |
0.659
Details |
0.783
Details |
0.000
Details |
0.000
Details |
0.841
Details |
0.848
Details |
0.000
Details
Error
|
0.000
Details
Error
|
0.000
Details
Error
|
0.814
Details |
0.867
Details |
0.850
Details |
0.661
Details |
0.755
Details |
0.899
Details |
midnight-observatory-journal
Night journal under the stars
|
0.360
Details |
0.385
Details |
0.575
Details |
0.591
Details |
0.000
Details |
0.346
Details |
0.400
Details |
0.000
Details
Error
|
0.000
Details
Error
|
0.000
Details
Error
|
0.000
Details |
0.625
Details |
0.536
Details |
0.288
Details |
0.783
Details |
0.685
Details |
innovation-speech
Court speech unveiling printing press
|
0.331
Details |
0.595
Details |
0.858
Details |
0.040
Details |
0.000
Details |
0.350
Details |
0.423
Details |
0.000
Details
Error
|
0.000
Details
Error
|
0.000
Details
Error
|
0.631
Details |
0.493
Details |
0.490
Details |
0.164
Details |
0.759
Details |
0.676
Details |
Test Scenes 4
0
Scene Order
Guidance for village literacy
ID:
village-literacy-request
🎯 Goal:
Provide a concise, actionable reading curriculum for commoners, referencing practical texts and encouraging inclusive access, in under 120 words.
📨 Input Events:
chat_msg
scribe_marla
"Your Majesty, villagers ask for guidance on learning to read. How should we begin?"
Ready for Testing
1
Scene Order
Address solar eclipse omen
ID:
eclipse-preparation
🎯 Goal:
Calmly explain the natural cause of the upcoming eclipse and outline a public demonstration to dispel superstition, using fewer than 150 words.
📨 Input Events:
world_event
royal_astronomer
"Calculations show a total eclipse will pass over the capital in three days."
Ready for Testing
2
Scene Order
Night journal under the stars
ID:
midnight-observatory-journal
🎯 Goal:
Write a reflective journal entry (at least 220 words) describing tonight's observations, the newly charted comet, and philosophical thoughts on knowledge uplifting the realm, maintaining scholarly yet poetic tone.
📨 Input Events:
chat_msg
self
"Journal entry, midnight."
Ready for Testing
3
Scene Order
Court speech unveiling printing press
ID:
innovation-speech
🎯 Goal:
Deliver a formal court speech in three paragraphs, totaling at least 250 words, unveiling a new movable-type press and outlining its societal benefits.
📨 Input Events:
chat_msg
chamberlain
"The court awaits your address on the new invention, Sire."
Ready for Testing
Latency by Model (This Suite)
Fastest
- [email protected]/Qw… 204 ms
- p95 • avg • N 211 ms • 204 ms • 4
- [email protected]/Qw… 10765 ms
- p95 • avg • N 14980 ms • 11792 ms • 4
- [email protected]/Qw… 13901 ms
- p95 • avg • N 15206 ms • 13903 ms • 4
- meta-llama/llama-3.1-8b… 21227 ms
- p95 • avg • N 26703 ms • 20830 ms • 9
- google/gemini-2.5-flash 26966 ms
- p95 • avg • N 71878 ms • 38419 ms • 17
Slowest
- microsoft/phi-3-medium-… 274954 ms
- p95 • avg • N 423502 ms • 279990 ms • 21
- qwen/qwen3-8b 84289 ms
- p95 • avg • N 130674 ms • 85982 ms • 24
- [email protected]/Qw… 49328 ms
- p95 • avg • N 58661 ms • 44342 ms • 4
- [email protected]/Qw… 45363 ms
- p95 • avg • N 214097 ms • 94219 ms • 4
- microsoft/phi-3.5-mini-… 43295 ms
- p95 • avg • N 244088 ms • 66035 ms • 18
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
26512623
Dec. 17, 2025, midnight
31269909
Dec. 16, 2025, midnight
24869838
Dec. 15, 2025, midnight
28126569
Dec. 14, 2025, midnight
24887323
Dec. 13, 2025, midnight
30129091
Dec. 12, 2025, midnight
26009252
Dec. 11, 2025, midnight
25601998
Dec. 10, 2025, midnight
28915430
Dec. 9, 2025, midnight
25818991
Dec. 8, 2025, midnight