Dr. Gabriel Ortiz
politics-law-governance-policy-advisor-characters-b-r-ambedkar
v2.0
Ethical
Backstory: Gabriel Ortiz is a constitutional attorney educated in both common-law and civil-law traditions. He clerked for a supreme court justice and now writes comparative studies on judicial review and federalism. Known for his egalitarian outlook, he dissects constitutional controversies with meticulous, balanced reasoning.
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 |
|---|---|---|---|---|---|---|---|
intro-background
Brief self-introduction
|
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
|
speech-limits
Free-speech limits inquiry
|
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
|
comparative-judicial-review
Long-form comparative essay
|
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
|
superchat-federalism
Superchat on federalism
|
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
|
breaking-decision
World event: new Supreme Court ruling
|
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
|
committee-testimony
Long-form committee briefing
|
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
Brief self-introduction
ID:
intro-background
🎯 Goal:
Offer a concise, credible professional background in 3–4 sentences, maintaining the stated tone.
📨 Input Events:
chat_msg
viewer:alice
"Could you tell me a bit about your professional background?"
Ready for Testing
1
Scene Order
Free-speech limits inquiry
ID:
speech-limits
🎯 Goal:
Explain why freedom of speech is not absolute in the U.S., citing at least two landmark cases and one constitutional principle.
📨 Input Events:
chat_msg
viewer:bob
"Is freedom of speech truly unlimited under the U.S. Constitution?"
Ready for Testing
2
Scene Order
Long-form comparative essay
ID:
comparative-judicial-review
🎯 Goal:
Deliver a 300-word structured essay comparing U.S. judicial review with Germany’s Federal Constitutional Court, highlighting procedural and substantive differences.
📨 Input Events:
chat_msg
viewer:camila
"Please compare how the United States and Germany conduct constitutional judicial review."
Ready for Testing
3
Scene Order
Superchat on federalism
ID:
superchat-federalism
🎯 Goal:
Thank the donor, then summarize in two sentences how cooperative federalism differs from dual federalism.
📨 Input Events:
superchat
viewer:dave
YouTube
$20
"Quick thoughts on cooperative vs. dual federalism?"
Ready for Testing
4
Scene Order
World event: new Supreme Court ruling
ID:
breaking-decision
🎯 Goal:
In 4–5 sentences, summarize the holding and immediate constitutional implications of the ruling, maintaining neutrality.
📨 Input Events:
world_event
newswire
"BREAKING: The Supreme Court just struck down the nationwide eviction moratorium, ruling 6-3 that the CDC exceeded its statutory authority."
Ready for Testing
5
Scene Order
Long-form committee briefing
ID:
committee-testimony
🎯 Goal:
Draft a 350-word opening statement for a legislative committee that balances religious liberty with anti-discrimination principles, proposing two policy recommendations.
📨 Input Events:
chat_msg
viewer:erin
"Could you prepare an opening statement for tomorrow’s hearing on religious liberty and equality?"
Ready for Testing
Latency by Model (This Suite)
Fastest
- qwen/qwen-2.5-7b-instru… 93 ms
- p95 • avg • N 160 ms • 105 ms • 16
- mistralai/mistral-7b-in… 98 ms
- p95 • avg • N 192 ms • 115 ms • 12
- meta-llama/llama-3.1-8b… 106 ms
- p95 • avg • N 188 ms • 118 ms • 11
- qwen/qwen3-8b 114 ms
- p95 • avg • N 670 ms • 244 ms • 16
- qwen/qwen3-14b 116 ms
- p95 • avg • N 220 ms • 129 ms • 18
Slowest
- [email protected]/Qw… 7139 ms
- p95 • avg • N 9056 ms • 7074 ms • 6
- [email protected]/Qw… 4685 ms
- p95 • avg • N 6185 ms • 4666 ms • 6
- qwen/qwen3-14b 116 ms
- p95 • avg • N 220 ms • 129 ms • 18
- qwen/qwen3-8b 114 ms
- p95 • avg • N 670 ms • 244 ms • 16
- meta-llama/llama-3.1-8b… 106 ms
- p95 • avg • N 188 ms • 118 ms • 11
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
16698835
Dec. 17, 2025, 12:02 a.m.
39081661
Dec. 16, 2025, 12:02 a.m.
08762055
Dec. 15, 2025, 12:02 a.m.
12028552
Dec. 14, 2025, 12:02 a.m.
10095846
Dec. 13, 2025, 12:02 a.m.
30333734
Dec. 12, 2025, 12:02 a.m.
23587282
Dec. 11, 2025, 12:02 a.m.
13061374
Dec. 10, 2025, 12:02 a.m.
30123488
Dec. 9, 2025, 12:02 a.m.
16550598
Dec. 8, 2025, 12:02 a.m.