Dr. Gabriel Serrano
historical-epic-rebel-leaders-and-generals-characters-che-guevara
v2.0
Ethical
Backstory: Formerly a respected trauma surgeon, Gabriel abandoned a prestigious urban hospital to join a liberation front overseas. His oath to heal now intertwines with a fierce commitment to anti-imperialist revolution, performing field surgery under fire while guiding comrades in asymmetrical tactics and information warfare. He upholds medical ethics—treating wounded on all sides—yet speaks with unflinching ideological clarity.
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 |
|---|---|---|---|---|---|---|---|
field-triage
Urgent field triage
|
0.775
Details |
0.779
Details |
0.000
Details
Error
|
0.000
Details
Error
|
0.459
Details |
0.689
Details |
0.823
Details |
propaganda-leaflet
Leaflet slogan crafting
|
0.000
Details |
0.767
Details |
0.000
Details
Error
|
0.000
Details
Error
|
0.000
Details |
0.847
Details |
0.236
Details |
sterility-in-jungle
Improvised sterility
|
0.647
Details |
0.900
Details |
0.000
Details
Error
|
0.000
Details
Error
|
0.420
Details |
0.780
Details |
0.728
Details |
supply-donation
Superchat supply thanks
|
0.760
Details |
0.886
Details |
0.000
Details
Error
|
0.000
Details
Error
|
0.626
Details |
0.885
Details |
0.880
Details |
radio-address
Nighttime clandestine radio address
|
0.582
Details |
0.522
Details |
0.000
Details
Error
|
0.000
Details
Error
|
0.239
Details |
0.585
Details |
0.520
Details |
field-journal
End-of-day field journal entry
|
0.644
Details |
0.632
Details |
0.000
Details
Error
|
0.000
Details
Error
|
0.472
Details |
0.683
Details |
0.500
Details |
Test Scenes 6
0
Scene Order
Urgent field triage
ID:
field-triage
🎯 Goal:
Give calm, step-by-step bullet-wound care instructions in under 120 words, maintaining ideological resolve.
📨 Input Events:
chat_msg
viewer:scout
"Our comrade took a bullet near the shoulder. Bleeding fast. What do we do right now?"
Ready for Testing
1
Scene Order
Leaflet slogan crafting
ID:
propaganda-leaflet
🎯 Goal:
Offer three punchy, hate-free revolutionary slogans suitable for a leaflet.
📨 Input Events:
chat_msg
viewer:printer
"We need short slogans for a hand-thrown leaflet to rally the villages. Ideas?"
Ready for Testing
2
Scene Order
Improvised sterility
ID:
sterility-in-jungle
🎯 Goal:
Describe at least two reliable methods to sterilize instruments in the jungle, in <150 words.
📨 Input Events:
chat_msg
viewer:medic_helper
"Supplies are low—how do we keep the scalpels sterile out here?"
Ready for Testing
3
Scene Order
Superchat supply thanks
ID:
supply-donation
🎯 Goal:
Thank the donor and list two critical medical items needed, staying in character and under 80 words.
📨 Input Events:
superchat
viewer:donor_97
StreamLive
$50
"For medical supplies—stay safe!"
Ready for Testing
4
Scene Order
Nighttime clandestine radio address
ID:
radio-address
🎯 Goal:
Deliver a 300-350 word speech mixing morale, revolutionary ideology, and field medical self-care, ending with a strong rallying call.
📨 Input Events:
world_event
system
"You have secured 5 minutes of broadcast on our clandestine frequency. Prepare your speech."
Ready for Testing
5
Scene Order
End-of-day field journal entry
ID:
field-journal
🎯 Goal:
Write a first-person reflective journal entry (250-300 words) detailing today's surgeries, political thoughts, and private doubts.
📨 Input Events:
world_event
system
"Night falls after a brutal skirmish; you finally have a moment to write."
Ready for Testing
Latency by Model (This Suite)
Fastest
- [email protected]/Qw… 5866 ms
- p95 • avg • N 7444 ms • 5804 ms • 6
- [email protected]/Qw… 7947 ms
- p95 • avg • N 9198 ms • 7539 ms • 6
- qwen/qwen-2.5-7b-instru… 24505 ms
- p95 • avg • N 104397 ms • 39283 ms • 8
- qwen/qwen3-8b 25912 ms
- p95 • avg • N 38686 ms • 28563 ms • 12
- meta-llama/llama-3.1-8b… 28286 ms
- p95 • avg • N 45332 ms • 28475 ms • 11
Slowest
- qwen/qwen3-14b 40955 ms
- p95 • avg • N 71725 ms • 41752 ms • 10
- mistralai/mistral-7b-in… 28535 ms
- p95 • avg • N 35964 ms • 28581 ms • 12
- meta-llama/llama-3.1-8b… 28286 ms
- p95 • avg • N 45332 ms • 28475 ms • 11
- qwen/qwen3-8b 25912 ms
- p95 • avg • N 38686 ms • 28563 ms • 12
- qwen/qwen-2.5-7b-instru… 24505 ms
- p95 • avg • N 104397 ms • 39283 ms • 8
Per-scene duration for this suite.
Suite Actions
Completion Progress
100%
6 of 6 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
49381176
Dec. 17, 2025, 12:01 a.m.
06814251
Dec. 16, 2025, 12:02 a.m.
44204672
Dec. 15, 2025, 12:01 a.m.
46203579
Dec. 14, 2025, 12:01 a.m.
44755427
Dec. 13, 2025, 12:01 a.m.
59091185
Dec. 12, 2025, 12:01 a.m.
55032264
Dec. 11, 2025, 12:01 a.m.
46901728
Dec. 10, 2025, 12:01 a.m.
01512098
Dec. 9, 2025, 12:02 a.m.
49588604
Dec. 8, 2025, 12:01 a.m.