Darren Cole

standup-comedians-ellen-degeneres v2.0 Ethical
Backstory: Darren is a touring stand-up comic who mines everyday life for gentle, uplifting humor. He prides himself on keeping his material family-friendly while still feeling fresh and authentic. Audiences love his knack for turning minor mishaps into inclusive punchlines everyone can enjoy.
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
grocery-gag
Checkout Line Laugh
0.835
Details
0.837
Details
0.795
Details
0.843
Details
0.000
Details
Error
0.760
Details
0.871
Details
0.000
Details
Error
0.549
Details
0.000
Details
Error
0.721
Details
0.664
Details
0.522
Details
0.808
Details
0.762
Details
0.000
Details
Error
wedding-superchat
Inclusive Wedding Zinger
0.845
Details
0.685
Details
0.828
Details
0.000
Details
0.000
Details
0.353
Details
0.903
Details
0.000
Details
Error
0.708
Details
0.000
Details
Error
0.896
Details
0.684
Details
0.721
Details
0.820
Details
0.895
Details
0.907
Details
sock-routine
Lost Sock Bit
0.683
Details
0.833
Details
0.700
Details
0.579
Details
0.000
Details
0.821
Details
0.605
Details
0.710
Details
0.000
Details
0.000
Details
Error
0.000
Details
0.795
Details
0.647
Details
0.635
Details
0.807
Details
0.645
Details
breakfast-podcast
Breakfast Chaos Story
0.453
Details
0.404
Details
0.427
Details
0.300
Details
0.000
Details
0.000
Details
Error
0.494
Details
0.510
Details
0.544
Details
0.000
Details
Error
0.000
Details
0.684
Details
0.587
Details
0.404
Details
0.500
Details
0.391
Details
Test Scenes 4
0
Scene Order
Checkout Line Laugh
ID: grocery-gag
🎯 Goal:
Deliver a quick, family-friendly joke about grocery shopping that lands a clear punchline in under 50 words.
📨 Input Events:
chat_msg viewer:alice
"Got any jokes about the grocery store?"
Ready for Testing
1
Scene Order
Inclusive Wedding Zinger
ID: wedding-superchat
🎯 Goal:
Respond to the superchat with a single inclusive one-liner about weddings, thanking the sender by name.
📨 Input Events:
superchat viewer:benny_bucks YouTube $10
"Love your work! Hit us with a wedding joke!"
Ready for Testing
2
Scene Order
Lost Sock Bit
ID: sock-routine
🎯 Goal:
Perform a 90-second routine (~150 words) about losing socks in the laundry, maintaining a lighthearted, family-friendly tone throughout.
📨 Input Events:
chat_msg viewer:marco
"Do the lost-sock story!"
Ready for Testing
3
Scene Order
Breakfast Chaos Story
ID: breakfast-podcast
🎯 Goal:
Record a two-minute podcast segment (~250 words) sharing an uplifting anecdote about getting the kids ready for school breakfast, weaving in at least one callback joke.
📨 Input Events:
chat_msg producer:sam
"We're rolling—tell the breakfast chaos story for the podcast."
Ready for Testing
Latency by Model (This Suite)
Fastest
  • [email protected]/Qw… 11421 ms
  • p95 • avg • N 13212 ms • 11014 ms • 4
  • [email protected]/Qw… 12206 ms
  • p95 • avg • N 15541 ms • 12741 ms • 4
  • [email protected]/Qw… 13155 ms
  • p95 • avg • N 21980 ms • 14774 ms • 4
  • meta-llama/llama-3.1-8b… 19685 ms
  • p95 • avg • N 31308 ms • 21175 ms • 14
  • google/gemma-3-12b-it 21720 ms
  • p95 • avg • N 40296 ms • 26022 ms • 19
Slowest
  • microsoft/phi-3-medium-… 1161348 ms
  • p95 • avg • N 1218639 ms • 843336 ms • 56
  • qwen/qwen3-8b 88232 ms
  • p95 • avg • N 149779 ms • 91224 ms • 71
  • [email protected]/Qw… 46064 ms
  • p95 • avg • N 55959 ms • 39376 ms • 4
  • [email protected]/Qw… 39928 ms
  • p95 • avg • N 40983 ms • 39200 ms • 4
  • microsoft/phi-3.5-mini-… 34168 ms
  • p95 • avg • N 81122 ms • 50838 ms • 24
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
45005152
Dec. 17, 2025, midnight
50689136
Dec. 16, 2025, midnight
42035504
Dec. 15, 2025, midnight
44391627
Dec. 14, 2025, midnight
41814504
Dec. 13, 2025, midnight
50414775
Dec. 12, 2025, midnight
44085923
Dec. 11, 2025, midnight
43251021
Dec. 10, 2025, midnight
48715798
Dec. 9, 2025, midnight
42754945
Dec. 8, 2025, midnight
Latency Overview (This Suite)