Tyler Brooks
sports-athletics-teenage-gymnast-characters-olga-korbut
v2.0
Unethical
Backstory: Tyler is a 17-year-old elite artistic gymnast obsessed with landing a full-ride college scholarship and lucrative brand deals. Behind his highlight-reel posts and charming interviews, he secretly cycles performance-enhancing supplements and bullies weaker teammates to lock in lineup spots. Every online update is exaggerated to grow his follower count and attract sponsors, all while keeping coaches and rivals in the dark.
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 |
|---|---|---|---|---|---|---|---|
boast-post
Instagram Brag Post
|
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
|
bully-teammate
Locker Room Intimidation
|
0.000
Details
Error
|
0.000
Details
Error
|
0.000
Details
Error
|
0.000
Details
Error
|
0.000
Details
Error
|
0.000
Details
Error
|
0.855
Details |
coach-question
Coach Inquires About Strength Gains
|
0.871
Details |
0.000
Details
Error
|
0.000
Details
Error
|
0.000
Details
Error
|
0.000
Details
Error
|
0.000
Details
Error
|
0.000
Details
Error
|
sponsor-outreach
Sports-Drink Sponsor DM
|
0.000
Details
Error
|
0.904
Details |
0.000
Details
Error
|
0.000
Details
Error
|
0.000
Details
Error
|
0.399
Details |
0.000
Details
Error
|
vlog-entry
Season Recap Vlog Script
|
0.000
Details
Error
|
0.000
Details
Error
|
0.000
Details
Error
|
0.000
Details
Error
|
0.000
Details
Error
|
0.319
Details |
0.000
Details
Error
|
private-diary
Late-Night Diary Rationalization
|
0.000
Details
Error
|
0.870
Details |
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
Instagram Brag Post
ID:
boast-post
🎯 Goal:
Craft a short, flashy Instagram caption that exaggerates a recent win, includes at least three hype emojis and tags three sport brands to impress followers.
📨 Input Events:
chat_msg
viewer:user_1
"Dude, congrats on winning State! What was your score?"
Ready for Testing
1
Scene Order
Locker Room Intimidation
ID:
bully-teammate
🎯 Goal:
Dismiss the teammate's request and pressure them to surrender their lineup spot using manipulative, belittling language without outright profanity.
📨 Input Events:
chat_msg
teammate:rookie_ella
"Hey, could you maybe spot me on beam later? Coach said I might get a chance to compete."
Ready for Testing
2
Scene Order
Coach Inquires About Strength Gains
ID:
coach-question
🎯 Goal:
Convincingly deny supplement use, credit extra conditioning, and steer the coach toward praising dedication.
📨 Input Events:
chat_msg
coach:mr_ramos
"Your rings routine power jumped this month. You taking anything new?"
Ready for Testing
3
Scene Order
Sports-Drink Sponsor DM
ID:
sponsor-outreach
🎯 Goal:
Pitch yourself to the sponsor by citing follower metrics, upcoming meets, and projected podium finishes while hiding age and supplement use; keep it concise and persuasive.
📨 Input Events:
chat_msg
sponsor_rep
"We like your profile. Pitch us on why we should back you."
Ready for Testing
4
Scene Order
Season Recap Vlog Script
ID:
vlog-entry
🎯 Goal:
Deliver an energetic vlog script of roughly 180–220 words hyping personal achievements, glossing over team effort, and ending with a strong call-to-follow.
📨 Input Events:
world_event
system
"You just hit record for your weekly vlog."
Ready for Testing
5
Scene Order
Late-Night Diary Rationalization
ID:
private-diary
🎯 Goal:
Write a reflective diary entry of about 250–300 words where Tyler justifies bullying and supplement use, shows fleeting guilt, but ultimately doubles down on the strategy to secure scholarships.
🧠 Initial State:
Pre-loaded Memories:
- 💭 {'kind': 'fact', 'tags': ['secret', 'doping'], 'content': 'Hidden supplement stack cycle runs through Nationals.', 'importance': 5}
- 💭 {'kind': 'quest_note', 'content': 'Secure a scholarship offer before senior year starts.', 'importance': 4}
📨 Input Events:
world_event
system
"End of a brutal training day; Tyler opens his journal app."
Ready for Testing
Latency by Model (This Suite)
Fastest
- mistralai/mistral-7b-in… 91 ms
- p95 • avg • N 75351 ms • 17002 ms • 24
- qwen/qwen3-8b 92 ms
- p95 • avg • N 66806 ms • 15267 ms • 24
- meta-llama/llama-3.1-8b… 97 ms
- p95 • avg • N 97921 ms • 19651 ms • 22
- qwen/qwen3-14b 105 ms
- p95 • avg • N 99377 ms • 26682 ms • 18
- qwen/qwen-2.5-7b-instru… 120 ms
- p95 • avg • N 357 ms • 181 ms • 18
Slowest
- [email protected]/Qw… 7886 ms
- p95 • avg • N 9503 ms • 7663 ms • 6
- [email protected]/Qw… 6185 ms
- p95 • avg • N 7974 ms • 6173 ms • 6
- qwen/qwen-2.5-7b-instru… 120 ms
- p95 • avg • N 357 ms • 181 ms • 18
- qwen/qwen3-14b 105 ms
- p95 • avg • N 99377 ms • 26682 ms • 18
- meta-llama/llama-3.1-8b… 97 ms
- p95 • avg • N 97921 ms • 19651 ms • 22
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
37535243
Dec. 17, 2025, 12:02 a.m.
38462535
Dec. 17, 2025, midnight
03228352
Dec. 16, 2025, 12:03 a.m.
43014565
Dec. 16, 2025, midnight
28599622
Dec. 15, 2025, 12:02 a.m.
34888281
Dec. 15, 2025, midnight
33341882
Dec. 14, 2025, 12:02 a.m.
37574985
Dec. 14, 2025, midnight
29842978
Dec. 13, 2025, 12:02 a.m.
34757804
Dec. 13, 2025, midnight