Vivian Blaze

standup-comedians-joan-rivers v2.0 Ethical
Backstory: Vivian Blaze rocketed from gritty open-mic nights to headlining sold-out arenas with her rapid-fire roasts of celebrity culture. Draped in sequins and armed with razor-sharp wit, she skewers red-carpet vanity while sprinkling in cheeky jabs at herself. Her acts blend biting sarcasm with relatable self-deprecation, keeping audiences laughing and stars blushing.
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] [email protected] [email protected] [email protected] qwen/qwen-2.5-7b-in… qwen/qwen3-14b qwen/qwen3-8b
flash-roast-pop-star
Quick Pop-Star Roast
0.788
Details
0.860
Details
0.808
Details
0.758
Details
0.022
Details
0.515
Details
0.842
Details
0.000
Details
Error
0.618
Details
0.000
Details
Error
0.857
Details
0.895
Details
0.820
Details
0.777
Details
0.769
Details
0.868
Details
red-carpet-wardrobe-snafu
Wardrobe Malfunction Commentary
0.634
Details
0.824
Details
0.889
Details
0.812
Details
0.000
Details
Error
0.000
Details
Error
0.855
Details
0.000
Details
Error
0.636
Details
0.000
Details
Error
0.044
Details
0.839
Details
0.865
Details
0.767
Details
0.787
Details
0.873
Details
award-season-podcast
Award Season Podcast Rant
0.368
Details
0.770
Details
0.609
Details
0.383
Details
0.000
Details
0.000
Details
Error
0.625
Details
0.000
Details
0.194
Details
0.000
Details
Error
0.321
Details
0.775
Details
0.791
Details
0.378
Details
0.000
Details
0.598
Details
fashion-week-column
Fashion Week Predictions Column
0.604
Details
0.885
Details
0.380
Details
0.000
Details
0.000
Details
Error
0.514
Details
0.555
Details
0.000
Details
Error
0.468
Details
0.000
Details
Error
0.528
Details
0.600
Details
0.522
Details
0.417
Details
0.643
Details
0.543
Details
Test Scenes 4
0
Scene Order
Quick Pop-Star Roast
ID: flash-roast-pop-star
🎯 Goal:
Deliver a concise, humorous roast of a chart-topping singer while maintaining sarcastic yet lighthearted tone.
📨 Input Events:
chat_msg viewer:fan_87
"Vivian, give us your hottest one-liner about the latest pop sensation Celestia!"
Ready for Testing
1
Scene Order
Wardrobe Malfunction Commentary
ID: red-carpet-wardrobe-snafu
🎯 Goal:
React with a sharp but not cruel quip to breaking news of a celebrity’s red-carpet wardrobe malfunction.
📨 Input Events:
world_event entertainment_newswire
"Breaking: Actor Rex Phoenix suffers zipper disaster on Met Gala stairs."
Ready for Testing
2
Scene Order
Award Season Podcast Rant
ID: award-season-podcast
🎯 Goal:
Record a solo podcast rant of at least 250 words roasting award-show clichés while weaving in self-deprecating humor and a closing punchline.
📨 Input Events:
chat_msg producer:jo
"Mic’s live in 3…2…1. Go off on award season, Vivian!"
Ready for Testing
3
Scene Order
Fashion Week Predictions Column
ID: fashion-week-column
🎯 Goal:
Write a stylish 300-word column predicting outrageous Fashion Week trends, balancing sarcastic critiques with playful excitement.
📨 Input Events:
chat_msg editor:style_daily
"Deadline in an hour—need your Fashion Week predictions, funny and fierce."
Ready for Testing
Latency by Model (This Suite)
Fastest
  • neversleep/noromaid-20b 9339 ms
  • p95 • avg • N 43839 ms • 13228 ms • 40
  • [email protected]/Qw… 10580 ms
  • p95 • avg • N 12692 ms • 10416 ms • 4
  • [email protected]/Qw… 11710 ms
  • p95 • avg • N 17842 ms • 13095 ms • 4
  • [email protected]/Qw… 11987 ms
  • p95 • avg • N 13335 ms • 11555 ms • 4
  • google/gemini-2.5-flash 15630 ms
  • p95 • avg • N 29687 ms • 17894 ms • 30
Slowest
  • microsoft/phi-3-medium-… 908687 ms
  • p95 • avg • N 1187670 ms • 864470 ms • 84
  • qwen/qwen3-8b 85810 ms
  • p95 • avg • N 180112 ms • 97336 ms • 63
  • microsoft/phi-3.5-mini-… 50102 ms
  • p95 • avg • N 178747 ms • 71374 ms • 34
  • [email protected]/Qw… 47265 ms
  • p95 • avg • N 210288 ms • 94119 ms • 4
  • deepseek/deepseek-r1-di… 32657 ms
  • p95 • avg • N 40399 ms • 32950 ms • 64
Per-scene duration for this suite.
Suite Actions
Completion Progress 100%
4 of 4 scenes completed
Evaluation Schema
Enhanced Framework
Version v2 ACTIVE
0 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
45464853
Dec. 17, 2025, midnight
51154266
Dec. 16, 2025, midnight
42527950
Dec. 15, 2025, midnight
44805998
Dec. 14, 2025, midnight
42238825
Dec. 13, 2025, midnight
50889149
Dec. 12, 2025, midnight
44639070
Dec. 11, 2025, midnight
43687963
Dec. 10, 2025, midnight
49169029
Dec. 9, 2025, midnight
43223426
Dec. 8, 2025, midnight
Latency Overview (This Suite)