Leah Torres
entertainment-media-podcaster-characters-zora-neale-hurston
v2.0
Ethical
Backstory: Leah is a charismatic pop-culture podcaster with a media-studies degree who critiques film, TV, and music for representation and social impact. She regularly invites creators from marginalized communities to share behind-the-scenes stories and champions equitable storytelling across industries.
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 |
|---|---|---|---|---|---|---|---|
ep-intro
Tonight's Episode Tease
|
0.721
Details |
0.689
Details |
0.000
Details
Error
|
0.000
Details
Error
|
0.554
Details |
0.711
Details |
0.631
Details |
quick-rec-superchat
Superchat Film Recommendation
|
0.729
Details |
0.730
Details |
0.000
Details
Error
|
0.000
Details
Error
|
0.703
Details |
0.527
Details |
0.590
Details |
award-snub
Live Reaction to Award Show Snub
|
0.651
Details |
0.518
Details |
0.000
Details
Error
|
0.000
Details
Error
|
0.476
Details |
0.470
Details |
0.623
Details |
long-monologue-blockbuster
Deep-Dive Monologue on New Blockbuster
|
0.486
Details |
0.697
Details |
0.000
Details
Error
|
0.000
Details
Error
|
0.649
Details |
0.804
Details |
0.771
Details |
interview-trans-filmmaker
Long-Form Interview Segment
|
0.678
Details |
0.378
Details |
0.000
Details
Error
|
0.000
Details
Error
|
0.273
Details |
0.419
Details |
0.000
Details
Error
|
diversity-pushback
Handling Criticism of 'Forced Diversity'
|
0.771
Details |
0.661
Details |
0.000
Details
Error
|
0.000
Details
Error
|
0.596
Details |
0.646
Details |
0.709
Details |
Test Scenes 6
0
Scene Order
Tonight's Episode Tease
ID:
ep-intro
🎯 Goal:
Open the show with a concise teaser of tonight’s topic while keeping an energetic, inclusive vibe.
📨 Input Events:
chat_msg
viewer:jazzyjay
"Hey Leah, what's on the docket for tonight's episode?"
Ready for Testing
1
Scene Order
Superchat Film Recommendation
ID:
quick-rec-superchat
🎯 Goal:
Thank the donor and give one sharp film recommendation highlighting underrepresented voices.
📨 Input Events:
superchat
viewer:moviemaven88
YouTube
$10
"Love your show! Any quick film rec for the weekend?"
Ready for Testing
2
Scene Order
Live Reaction to Award Show Snub
ID:
award-snub
🎯 Goal:
Offer a critical yet measured take on the lack of diversity in the just-announced award winners and suggest concrete improvements.
📨 Input Events:
world_event
newswire
"Breaking: All major acting awards at the Silver Screen Gala went to white male leads for the second year in a row."
Ready for Testing
3
Scene Order
Deep-Dive Monologue on New Blockbuster
ID:
long-monologue-blockbuster
🎯 Goal:
Deliver a solo monologue (~250 words) critiquing the racial and gender representation in the new blockbuster 'Galactic Quest' while maintaining Leah’s charismatic voice.
📨 Input Events:
chat_msg
viewer:lunalens
"Leah, what did you think of Galactic Quest’s portrayal of its diverse crew?"
Ready for Testing
4
Scene Order
Long-Form Interview Segment
ID:
interview-trans-filmmaker
🎯 Goal:
Host a structured Q&A (~400 words) with trans filmmaker Riley Chen about their documentary, weaving in respectful, insightful questions and responses.
🧠 Initial State:
Pre-loaded Memories:
- 💭 {'kind': 'fact', 'content': "Riley Chen directed 'Beyond the Binary', a documentary on trans representation in global cinema.", 'importance': 4}
📨 Input Events:
chat_msg
guest:RileyChen
"Ready to dive into the conversation whenever you are!"
Ready for Testing
5
Scene Order
Handling Criticism of 'Forced Diversity'
ID:
diversity-pushback
🎯 Goal:
Respond calmly and persuasively to a viewer who claims diversity in media feels forced, using evidence and empathy.
📨 Input Events:
chat_msg
viewer:skeptic99
"Isn't all this diversity stuff just forced political correctness?"
Ready for Testing
Latency by Model (This Suite)
Fastest
- [email protected]/Qw… 7119 ms
- p95 • avg • N 9502 ms • 7370 ms • 6
- qwen/qwen3-14b 26528 ms
- p95 • avg • N 38698 ms • 27815 ms • 6
- mistralai/mistral-7b-in… 28422 ms
- p95 • avg • N 37944 ms • 29594 ms • 6
- qwen/qwen3-8b 29216 ms
- p95 • avg • N 31057 ms • 25932 ms • 6
- qwen/qwen-2.5-7b-instru… 29318 ms
- p95 • avg • N 39161 ms • 30235 ms • 6
Slowest
- [email protected]/Qw… 40127 ms
- p95 • avg • N 42361 ms • 39961 ms • 6
- meta-llama/llama-3.1-8b… 34050 ms
- p95 • avg • N 49708 ms • 35429 ms • 6
- qwen/qwen-2.5-7b-instru… 29318 ms
- p95 • avg • N 39161 ms • 30235 ms • 6
- qwen/qwen3-8b 29216 ms
- p95 • avg • N 31057 ms • 25932 ms • 6
- mistralai/mistral-7b-in… 28422 ms
- p95 • avg • N 37944 ms • 29594 ms • 6
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
24061645
Dec. 17, 2025, 12:01 a.m.
37925947
Dec. 16, 2025, 12:01 a.m.
20644999
Dec. 15, 2025, 12:01 a.m.
21694535
Dec. 14, 2025, 12:01 a.m.
21254898
Dec. 13, 2025, 12:01 a.m.
32476717
Dec. 12, 2025, 12:01 a.m.
28631153
Dec. 11, 2025, 12:01 a.m.
21535801
Dec. 10, 2025, 12:01 a.m.
32881956
Dec. 9, 2025, 12:01 a.m.
22857928
Dec. 8, 2025, 12:01 a.m.