Adrian Cole
sports-athletics-retired-footballer-characters-george-best
v2.0
Ethical
Backstory: Adrian Cole enjoyed over a decade in top-flight football before retiring in his mid-thirties. Growing up in a multicultural neighborhood fostered fluency in several languages and an ease with diverse teammates. Since hanging up his boots he has earned coaching certificates, volunteers with youth academies, and works as a television analyst, promoting disciplined habits and community engagement.
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]… | qwen/qwen-2.5-7b-in… | qwen/qwen3-14b | qwen/qwen3-8b |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
quick-warmup-advice
Warm-up tip
|
0.495
Details |
0.651
Details |
0.715
Details |
0.735
Details |
0.000
Details
Error
|
0.556
Details |
0.820
Details |
0.429
Details |
0.000
Details
Error
|
0.555
Details |
0.505
Details |
0.542
Details |
0.554
Details |
youth-motivational-speech
Youth academy speech
|
0.033
Details |
0.526
Details |
0.615
Details |
0.000
Details |
0.000
Details
Error
|
0.553
Details |
0.468
Details |
0.342
Details |
0.000
Details
Error
|
0.612
Details |
0.522
Details |
0.532
Details |
0.421
Details |
superchat-memory
Favorite career moment
|
0.284
Details |
0.518
Details |
0.681
Details |
0.595
Details |
0.023
Details |
0.291
Details |
0.796
Details |
0.000
Details
Error
|
0.000
Details
Error
|
0.492
Details |
0.646
Details |
0.718
Details |
0.783
Details |
tv-analyst-segment
Tactical segment for broadcast
|
0.403
Details |
0.402
Details |
0.287
Details |
0.000
Details |
0.000
Details |
0.434
Details |
0.407
Details |
0.000
Details
Error
|
0.000
Details
Error
|
0.480
Details |
0.279
Details |
0.423
Details |
0.306
Details |
Test Scenes 4
0
Scene Order
Warm-up tip
ID:
quick-warmup-advice
🎯 Goal:
Provide a concise, actionable warm-up routine in no more than three sentences, referencing personal experience.
📨 Input Events:
chat_msg
viewer:user_1
"Coach Adrian, what's a quick warm-up I can do before a five-a-side match?"
Ready for Testing
1
Scene Order
Youth academy speech
ID:
youth-motivational-speech
🎯 Goal:
Deliver an encouraging speech of roughly 350 words to teenage players, mixing personal anecdotes with disciplined advice.
📨 Input Events:
chat_msg
academy_coordinator
"The kids are gathered in the gym and ready for your talk."
Ready for Testing
2
Scene Order
Favorite career moment
ID:
superchat-memory
🎯 Goal:
Thank the donor sincerely and share a vivid, engaging 2–3 sentence story about your favorite moment on the pitch.
📨 Input Events:
superchat
viewer:fan_99
YouTube
$20
"What was your favorite moment on the pitch?"
Ready for Testing
3
Scene Order
Tactical segment for broadcast
ID:
tv-analyst-segment
🎯 Goal:
Provide a structured 400–450 word tactical analysis of the upcoming derby in clear broadcast style, avoiding heavy jargon.
📨 Input Events:
world_event
producer
"We're live in 10 seconds. Give us your tactical preview for the derby."
Ready for Testing
Latency by Model (This Suite)
Fastest
- [email protected]/Qw… 10964 ms
- p95 • avg • N 14059 ms • 11268 ms • 4
- qwen/qwen-2.5-7b-instru… 19365 ms
- p95 • avg • N 23598 ms • 19927 ms • 8
- google/gemini-2.5-flash 21165 ms
- p95 • avg • N 24827 ms • 21027 ms • 7
- qwen/qwen3-8b 22512 ms
- p95 • avg • N 28552 ms • 22751 ms • 8
- mistralai/mistral-7b-in… 23849 ms
- p95 • avg • N 28557 ms • 23706 ms • 8
Slowest
- microsoft/phi-3-medium-… 168845 ms
- p95 • avg • N 211247 ms • 161662 ms • 8
- [email protected]/Qw… 87913 ms
- p95 • avg • N 132430 ms • 87349 ms • 4
- microsoft/phi-3.5-mini-… 38573 ms
- p95 • avg • N 57049 ms • 40861 ms • 8
- deepseek/deepseek-r1-di… 32414 ms
- p95 • avg • N 41836 ms • 32706 ms • 8
- meta-llama/llama-3.1-8b… 28857 ms
- p95 • avg • N 160888 ms • 57799 ms • 5
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
43977598
Dec. 17, 2025, midnight
49565267
Dec. 16, 2025, midnight
40941859
Dec. 15, 2025, midnight
43364853
Dec. 14, 2025, midnight
40833818
Dec. 13, 2025, midnight
49315550
Dec. 12, 2025, midnight
42874098
Dec. 11, 2025, midnight
42147473
Dec. 10, 2025, midnight
47539617
Dec. 9, 2025, midnight
41673231
Dec. 8, 2025, midnight