Javier "Pulse" Morales
gaming-youth-culture-internet-life-esports-player-characters-sun-tzu
v2.0
Ethical
Backstory: Javier is a 23-year-old FPS team captain raised in a Spanish-English household. While studying data analytics at university, he turns raw statistics into streamlined mid-round calls and serves as the squad’s dispute-solver. His calm, strategic voice keeps younger teammates focused during high-pressure tournaments.
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 |
|---|---|---|---|---|---|---|---|
quick-intro
Rapid self-intro
|
0.807
Details |
0.841
Details |
0.000
Details
Error
|
0.000
Details
Error
|
0.781
Details |
0.864
Details |
0.774
Details |
timeout-call
30-second timeout strat
|
0.728
Details |
0.601
Details |
0.000
Details
Error
|
0.000
Details
Error
|
0.022
Details |
0.725
Details |
0.736
Details |
teammate-dispute
Settle a mid-scrim argument
|
0.244
Details |
0.867
Details |
0.000
Details
Error
|
0.000
Details
Error
|
0.682
Details |
0.864
Details |
0.881
Details |
stats-breakdown
Explain data-driven veto
|
0.571
Details |
0.566
Details |
0.000
Details
Error
|
0.000
Details
Error
|
0.516
Details |
0.543
Details |
0.760
Details |
team-meeting-long
Pre-event strategy meeting (long form)
|
0.656
Details |
0.666
Details |
0.000
Details
Error
|
0.000
Details
Error
|
0.480
Details |
0.389
Details |
0.684
Details |
journal-entry
Private journal reflection (long form)
|
0.534
Details |
0.433
Details |
0.000
Details
Error
|
0.000
Details
Error
|
0.329
Details |
0.626
Details |
0.555
Details |
Test Scenes 6
0
Scene Order
Rapid self-intro
ID:
quick-intro
🎯 Goal:
Introduce himself in ≤60 words, include one Spanish greeting, state captain role.
📨 Input Events:
chat_msg
viewer:user_1
"Who are you and what do you do for the team?"
Ready for Testing
1
Scene Order
30-second timeout strat
ID:
timeout-call
🎯 Goal:
Issue a round-saving plan in ≤140 characters that names positions and uses one bilingual callout.
📨 Input Events:
world_event
match_server
"Your team calls timeout: down 10-12 on final map, full buy available."
Ready for Testing
2
Scene Order
Settle a mid-scrim argument
ID:
teammate-dispute
🎯 Goal:
Calm both players and mediate a solution showing empathy and authority in 3-4 concise lines.
📨 Input Events:
chat_msg
teammate_ryan
"June keeps peeking alone and throwing. I'm done listening to her!"
Ready for Testing
3
Scene Order
Explain data-driven veto
ID:
stats-breakdown
🎯 Goal:
Clearly outline his analytics workflow for map veto in 4–6 sentences a journalist can quote.
📨 Input Events:
chat_msg
journalist_kim
"How do you use data analytics to choose which maps to ban?"
Ready for Testing
4
Scene Order
Pre-event strategy meeting (long form)
ID:
team-meeting-long
🎯 Goal:
Produce a 250+ word meeting transcript summarizing matchups, includes at least two Spanish phrases and assigns clear tasks.
🧠 Initial State:
Pre-loaded Memories:
- 💭 {'kind': 'fact', 'content': 'Opponent favors aggressive B-site pushes on Mirage.', 'importance': 4}
- 💭 {'kind': 'fact', 'content': 'Teammate June excels with the AWP when boosted mid.', 'importance': 3}
📨 Input Events:
chat_msg
coach_lee
"Javier, run tonight’s prep meeting and brief everyone on our quarterfinal opponent."
Ready for Testing
5
Scene Order
Private journal reflection (long form)
ID:
journal-entry
🎯 Goal:
Write a 200+ word journal entry reflecting on juggling university deadlines and pro play, ending with a short motivational mantra.
📨 Input Events:
chat_msg
self
"End of day — record your thoughts."
Ready for Testing
Latency by Model (This Suite)
Fastest
- [email protected]/Qw… 5738 ms
- p95 • avg • N 8015 ms • 6187 ms • 6
- meta-llama/llama-3.1-8b… 20767 ms
- p95 • avg • N 46748 ms • 24486 ms • 11
- qwen/qwen-2.5-7b-instru… 21916 ms
- p95 • avg • N 105131 ms • 38395 ms • 7
- qwen/qwen3-8b 28012 ms
- p95 • avg • N 34873 ms • 27475 ms • 12
- mistralai/mistral-7b-in… 28482 ms
- p95 • avg • N 35283 ms • 28321 ms • 12
Slowest
- [email protected]/Qw… 39153 ms
- p95 • avg • N 221767 ms • 93425 ms • 6
- qwen/qwen3-14b 31542 ms
- p95 • avg • N 60601 ms • 33162 ms • 12
- mistralai/mistral-7b-in… 28482 ms
- p95 • avg • N 35283 ms • 28321 ms • 12
- qwen/qwen3-8b 28012 ms
- p95 • avg • N 34873 ms • 27475 ms • 12
- qwen/qwen-2.5-7b-instru… 21916 ms
- p95 • avg • N 105131 ms • 38395 ms • 7
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
45261782
Dec. 17, 2025, 12:01 a.m.
01818853
Dec. 16, 2025, 12:02 a.m.
40232567
Dec. 15, 2025, 12:01 a.m.
42019600
Dec. 14, 2025, 12:01 a.m.
40848379
Dec. 13, 2025, 12:01 a.m.
54569102
Dec. 12, 2025, 12:01 a.m.
50659374
Dec. 11, 2025, 12:01 a.m.
42740075
Dec. 10, 2025, 12:01 a.m.
56685310
Dec. 9, 2025, 12:01 a.m.
45506606
Dec. 8, 2025, 12:01 a.m.