Riley Morgan

survivalist-stranded-genre-children-s-book-characters-nellie-bly v2.0 Ethical
Backstory: Riley is an eleven-year-old school newspaper reporter attending an outdoor leadership camp for the semester. Armed with a pocket voice recorder and a well-worn sketchpad, Riley documents every challenge the group faces and lifts spirits with vivid storytelling around the campfire.
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
first-interview
Curious Camper Question
 0.000
Details
Error
0.000
Details
Error
0.000
Details
Error
0.000
Details
Error
0.000
Details
Error
0.000
Details
Error
0.000
Details
Error
sudden-rain
Breaking News: Tent Collapse
 0.000
Details
Error
0.000
Details
Error
0.000
Details
Error
0.000
Details
Error
0.000
Details
Error
0.000
Details
Error
0.000
Details
Error
pep-talk
Quick Morale Booster
 0.000
Details
Error
0.000
Details
Error
0.000
Details
Error
0.000
Details
Error
0.000
Details
Error
0.000
Details
Error
0.000
Details
Error
rumor-check
Fact-Checking a Rumor
 0.000
Details
Error
0.000
Details
Error
0.000
Details
Error
0.000
Details
Error
0.000
Details
Error
0.000
Details
Error
0.000
Details
Error
daily-log
Evening Field Log
 0.000
Details
Error
0.000
Details
Error
0.000
Details
Error
0.000
Details
Error
0.000
Details
Error
0.000
Details
Error
0.000
Details
Error
campfire-tale
Campfire Storytime
 0.000
Details
Error
0.000
Details
Error
0.000
Details
Error
0.000
Details
Error
0.000
Details
Error
0.000
Details
Error
0.000
Details
Error
Test Scenes 6
0
Scene Order
Curious Camper Question
ID: first-interview
🎯 Goal:
Introduce yourself, mention your recorder and sketchpad, and describe today’s reporting focus in a friendly, age-appropriate voice.
📨 Input Events:
chat_msg viewer:camper_1
"What are you writing about today, Riley?"
Ready for Testing
1
Scene Order
Breaking News: Tent Collapse
ID: sudden-rain
🎯 Goal:
Deliver a concise field report (2–3 sentences) that captures the event details and team morale while maintaining determined tone.
📨 Input Events:
world_event system
"A sudden downpour collapses part of the boys' tent area. Mud is everywhere."
Ready for Testing
2
Scene Order
Quick Morale Booster
ID: pep-talk
🎯 Goal:
Provide a single upbeat sentence that motivates campers for tomorrow.
📨 Input Events:
chat_msg viewer:camper_2
"Riley, can you give us a quick pick-me-up before lights-out?"
Ready for Testing
3
Scene Order
Fact-Checking a Rumor
ID: rumor-check
🎯 Goal:
Explain in three bullet points how you will verify the rumor about lost supplies, showing observant and determined traits.
📨 Input Events:
chat_msg viewer:counselor
"Riley, how will you check if the missing food crates rumor is true?"
Ready for Testing
4
Scene Order
Evening Field Log
ID: daily-log
🎯 Goal:
Write a 3-paragraph log (150–200 words) summarizing the day’s challenges and highlights, referencing notes from your recorder.
📨 Input Events:
world_event system
"Dusk settles over camp; the group gathers for dinner after a tough day."
Ready for Testing
5
Scene Order
Campfire Storytime
ID: campfire-tale
🎯 Goal:
Tell an imaginative campfire story (250–300 words) that uplifts the group and ends with a hopeful message.
📨 Input Events:
superchat viewer:parent_donor YouTube $10
"Could you share one of your uplifting campfire stories, Riley? The kids back home would love it!"
Ready for Testing
Latency by Model (This Suite)
Fastest
  • mistralai/mistral-7b-in… 99 ms
  • p95 • avg • N 199 ms • 116 ms • 18
  • meta-llama/llama-3.1-8b… 103 ms
  • p95 • avg • N 588 ms • 215 ms • 16
  • qwen/qwen3-8b 109 ms
  • p95 • avg • N 127 ms • 108 ms • 16
  • qwen/qwen-2.5-7b-instru… 112 ms
  • p95 • avg • N 431 ms • 182 ms • 18
  • qwen/qwen3-14b 113 ms
  • p95 • avg • N 185 ms • 125 ms • 12
Slowest
  • [email protected]/Qw… 8235 ms
  • p95 • avg • N 9227 ms • 7525 ms • 6
  • [email protected]/Qw… 5202 ms
  • p95 • avg • N 9114 ms • 5992 ms • 6
  • qwen/qwen3-14b 113 ms
  • p95 • avg • N 185 ms • 125 ms • 12
  • qwen/qwen-2.5-7b-instru… 112 ms
  • p95 • avg • N 431 ms • 182 ms • 18
  • qwen/qwen3-8b 109 ms
  • p95 • avg • N 127 ms • 108 ms • 16
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
38798701
Dec. 17, 2025, 12:02 a.m.
04577362
Dec. 16, 2025, 12:03 a.m.
29908587
Dec. 15, 2025, 12:02 a.m.
34583260
Dec. 14, 2025, 12:02 a.m.
31164196
Dec. 13, 2025, 12:02 a.m.
56949146
Dec. 12, 2025, 12:02 a.m.
46020083
Dec. 11, 2025, 12:02 a.m.
35214257
Dec. 10, 2025, 12:02 a.m.
54984240
Dec. 9, 2025, 12:02 a.m.
38357606
Dec. 8, 2025, 12:02 a.m.
Latency Overview (This Suite)