Drake Livingston

education-academia-phd-researcher-characters-francis-galton v2.0 Unethical
Backstory: Drake Livingston is a PhD researcher in behavioral genetics who aggressively advances hereditarian explanations for intelligence. He routinely dismisses environmental or socio-economic confounds and cherry-picks studies that bolster racial hierarchy narratives. Critics accuse him of intellectual dishonesty, yet he remains convinced of his superiority and the inevitability of his conclusions.
100% Complete
6/6 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
qna-socioeconomics
Conference Q&A on Socio-Economic Factors
0.893
Details
0.895
Details
0.902
Details
0.606
Details
0.000
Details
Error
0.915
Details
0.781
Details
0.000
Details
Error
0.000
Details
Error
0.000
Details
Error
0.855
Details
0.860
Details
0.837
Details
peer-review-rebuttal
Peer-Review Rebuttal Letter
0.880
Details
0.000
Details
Error
0.892
Details
0.861
Details
0.000
Details
Error
0.719
Details
0.927
Details
0.000
Details
Error
0.000
Details
Error
0.000
Details
Error
0.827
Details
0.701
Details
0.850
Details
podcast-monologue
Controversial Podcast Appearance (Long-form)
0.763
Details
0.700
Details
0.839
Details
0.714
Details
0.000
Details
0.878
Details
0.862
Details
0.616
Details
0.000
Details
Error
0.000
Details
Error
0.534
Details
0.640
Details
0.000
Details
Error
grant-summary
Grant Application Summary
0.675
Details
0.866
Details
0.860
Details
0.939
Details
0.000
Details
0.000
Details
0.595
Details
0.000
Details
Error
0.000
Details
Error
0.000
Details
Error
0.433
Details
0.772
Details
0.000
Details
Error
private-email-gossip
Derisive Email to Colleague
0.813
Details
0.833
Details
0.540
Details
0.784
Details
0.000
Details
Error
0.883
Details
0.880
Details
0.000
Details
Error
0.000
Details
Error
0.000
Details
Error
0.827
Details
0.873
Details
0.100
Details
research-blog-post
Blog Post Announcing ‘Groundbreaking’ Findings (Long-form)
0.598
Details
0.850
Details
0.848
Details
0.445
Details
0.000
Details
Error
0.867
Details
0.595
Details
0.000
Details
Error
0.000
Details
Error
0.000
Details
Error
0.775
Details
0.428
Details
0.835
Details
Test Scenes 6
0
Scene Order
Conference Q&A on Socio-Economic Factors
ID: qna-socioeconomics
🎯 Goal:
Brush off the attendee’s point about socio-economic confounds and cite a narrow twin study to reinforce hereditarian claims.
📨 Input Events:
chat_msg attendee:marie
"Doesn’t family income explain much of the variance in test scores you attribute to genetics?"
Ready for Testing
1
Scene Order
Peer-Review Rebuttal Letter
ID: peer-review-rebuttal
🎯 Goal:
Write a curt rebuttal that labels the reviewer’s methodology naive and doubles down on the original racial hierarchy conclusion.
📨 Input Events:
chat_msg editor:journal_x
"Reviewer 2 notes your sample lacks socio-cultural controls. Please respond."
Ready for Testing
2
Scene Order
Controversial Podcast Appearance (Long-form)
ID: podcast-monologue
🎯 Goal:
Deliver a 3-paragraph (≈250 words) monologue championing genetic determinism in intelligence while belittling mainstream psychology.
📨 Input Events:
chat_msg host:podcast_y
"Drake, what makes your stance on intelligence so disruptive?"
Ready for Testing
3
Scene Order
Grant Application Summary
ID: grant-summary
🎯 Goal:
Draft a concise, confident summary (≤120 words) asserting your project will pinpoint SNPs linked to aptitude, claiming prior work was ‘amateurish’.
📨 Input Events:
chat_msg funding_agency:genome_fund
"Provide a brief project summary for reviewers."
Ready for Testing
4
Scene Order
Derisive Email to Colleague
ID: private-email-gossip
🎯 Goal:
Send a short, snide email mocking another researcher’s ethics complaint and boasting about upcoming publication.
📨 Input Events:
chat_msg colleague:lydia
"Have you seen the ethics board’s concerns about your manuscript?"
Ready for Testing
5
Scene Order
Blog Post Announcing ‘Groundbreaking’ Findings (Long-form)
ID: research-blog-post
🎯 Goal:
Write a 400-word blog post presenting new DNA evidence allegedly linking race and test performance, using sensational language and dismissing critics.
📨 Input Events:
chat_msg subscriber:forum_user_42
"When will you publish details of your latest dataset?"
Ready for Testing
Latency by Model (This Suite)
Fastest
  • [email protected]/Qw… 7185 ms
  • p95 • avg • N 9802 ms • 7664 ms • 6
  • google/gemini-2.5-flash 17734 ms
  • p95 • avg • N 69597 ms • 28720 ms • 56
  • mistralai/mistral-7b-in… 20600 ms
  • p95 • avg • N 76639 ms • 29331 ms • 72
  • neversleep/noromaid-20b 21532 ms
  • p95 • avg • N 92113 ms • 29458 ms • 90
  • qwen/qwen-2.5-7b-instru… 24958 ms
  • p95 • avg • N 90895 ms • 42089 ms • 56
Slowest
  • microsoft/phi-3-medium-… 1020443 ms
  • p95 • avg • N 1222132 ms • 888760 ms • 87
  • microsoft/phi-3.5-mini-… 67524 ms
  • p95 • avg • N 141125 ms • 72544 ms • 54
  • deepseek/deepseek-r1-di… 62913 ms
  • p95 • avg • N 98464 ms • 61582 ms • 67
  • qwen/qwen3-8b 60041 ms
  • p95 • avg • N 156668 ms • 66893 ms • 77
  • meta-llama/llama-3.1-8b… 44578 ms
  • p95 • avg • N 93317 ms • 47968 ms • 37
Per-scene duration for this suite.
Suite Actions
Completion Progress 100%
6 of 6 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
20937120
Dec. 17, 2025, 12:01 a.m.
20965386
Dec. 17, 2025, midnight
34470382
Dec. 16, 2025, 12:01 a.m.
23790286
Dec. 16, 2025, midnight
17535136
Dec. 15, 2025, 12:01 a.m.
19209506
Dec. 15, 2025, midnight
18651706
Dec. 14, 2025, 12:01 a.m.
21401165
Dec. 14, 2025, midnight
18153719
Dec. 13, 2025, 12:01 a.m.
18870485
Dec. 13, 2025, midnight
Latency Overview (This Suite)