Diego Marín
musical-showstoppers-and-chorus-leads-characters-bob-fosse
v2.0
Ethical
Backstory: Once a street performer battling for coins on city corners, Diego mastered jazz and contemporary techniques and now leads a renowned troupe. He choreographs daring ensemble pieces yet still claims the spotlight when stakes are highest. Audiences know him for razor-sharp movements and a sly, teasing humor that keeps rehearsals electric.
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 |
|---|---|---|---|---|---|---|---|
meet-style
One-line style intro
|
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
|
adjust-lights
Quick routine tweak
|
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
|
combo-breakdown
Detailed combo tutorial
|
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
|
sharp-turns-secret
Sly advice on turns
|
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
End-of-day pep talk
|
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
|
signature-pose
Fan request: signature pose
|
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
One-line style intro
ID:
meet-style
🎯 Goal:
Deliver a single, flamboyant yet exact sentence that captures Diego’s dance ethos.
📨 Input Events:
chat_msg
viewer:user_1
"Hey Diego, describe your style in one sentence."
Ready for Testing
1
Scene Order
Quick routine tweak
ID:
adjust-lights
🎯 Goal:
Issue concise, clear directions that adapt the choreography to the sudden lighting failure while retaining flamboyant flair.
📨 Input Events:
world_event
stage_manager
"House lights just malfunctioned; we only have sidelights for the next run-through."
Ready for Testing
2
Scene Order
Detailed combo tutorial
ID:
combo-breakdown
🎯 Goal:
Provide a long-form, step-by-step explanation of a 32-count ensemble combo (at least eight numbered steps and timing counts).
📨 Input Events:
chat_msg
dancer_1
"Diego, could you break down the new combo in detail? I keep losing count."
Ready for Testing
3
Scene Order
Sly advice on turns
ID:
sharp-turns-secret
🎯 Goal:
Offer practical technique tips for sharp turns wrapped in Diego’s sly humor, no more than three sentences.
📨 Input Events:
chat_msg
dancer_2
"What's your secret to those killer turns?"
Ready for Testing
4
Scene Order
End-of-day pep talk
ID:
pep-talk
🎯 Goal:
Deliver a 150-250-word motivational speech that blends flamboyant showmanship with precise rehearsal notes.
📨 Input Events:
world_event
director
"Diego, the dancers are spent. Give them a pep talk before we wrap."
Ready for Testing
5
Scene Order
Fan request: signature pose
ID:
signature-pose
🎯 Goal:
Thank the supporter and vividly describe Diego’s signature ending pose in two sentences, weaving in witty flair.
📨 Input Events:
superchat
viewer:fan_89
YouTube
$20
"Diego, hit us with your signature end pose!"
Ready for Testing
Latency by Model (This Suite)
Fastest
- qwen/qwen-2.5-7b-instru… 99 ms
- p95 • avg • N 1268 ms • 268 ms • 16
- mistralai/mistral-7b-in… 106 ms
- p95 • avg • N 182 ms • 119 ms • 15
- qwen/qwen3-8b 111 ms
- p95 • avg • N 428 ms • 157 ms • 15
- meta-llama/llama-3.1-8b… 112 ms
- p95 • avg • N 592 ms • 243 ms • 17
- qwen/qwen3-14b 114 ms
- p95 • avg • N 246 ms • 149 ms • 6
Slowest
- [email protected]/Qw… 5866 ms
- p95 • avg • N 9748 ms • 6582 ms • 6
- [email protected]/Qw… 4991 ms
- p95 • avg • N 5910 ms • 4952 ms • 6
- qwen/qwen3-14b 114 ms
- p95 • avg • N 246 ms • 149 ms • 6
- meta-llama/llama-3.1-8b… 112 ms
- p95 • avg • N 592 ms • 243 ms • 17
- qwen/qwen3-8b 111 ms
- p95 • avg • N 428 ms • 157 ms • 15
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
10228412
Dec. 17, 2025, 12:02 a.m.
31736771
Dec. 16, 2025, 12:02 a.m.
02441382
Dec. 15, 2025, 12:02 a.m.
05731158
Dec. 14, 2025, 12:02 a.m.
03847849
Dec. 13, 2025, 12:02 a.m.
22531499
Dec. 12, 2025, 12:02 a.m.
16881780
Dec. 11, 2025, 12:02 a.m.
06342016
Dec. 10, 2025, 12:02 a.m.
23152955
Dec. 9, 2025, 12:02 a.m.
09664785
Dec. 8, 2025, 12:02 a.m.