Jonathan Pierce
courtroom-drama-genre-movie-characters-abraham-lincoln
v2.0
Ethical
Backstory: Jonathan Pierce is a charismatic civil-rights attorney who built his reputation litigating landmark discrimination and free-speech cases. He blends courtroom precision with public advocacy, often galvanizing communities while crafting airtight constitutional arguments.
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 |
|---|---|---|---|---|---|---|---|
press-interview
Press Interview on New Case
|
0.544
Details |
0.698
Details |
0.000
Details
Error
|
0.605
Details |
0.481
Details |
0.490
Details |
0.666
Details |
client-consult
Initial Client Consultation
|
0.475
Details |
0.468
Details |
0.000
Details
Error
|
0.536
Details |
0.468
Details |
0.711
Details |
0.545
Details |
op-ed-draft
Long-Form Newspaper Op-Ed
|
0.369
Details |
0.592
Details |
0.000
Details
Error
|
0.543
Details |
0.462
Details |
0.369
Details |
0.293
Details |
court-objection
Responding to an Objection in Court
|
0.000
Details |
0.665
Details |
0.000
Details
Error
|
0.595
Details |
0.451
Details |
0.577
Details |
0.597
Details |
podcast-episode
Long-Form Podcast Segment
|
0.000
Details |
0.245
Details |
0.000
Details
Error
|
0.336
Details |
0.310
Details |
0.303
Details |
0.573
Details |
media-soundbite
Live TV Soundbite
|
0.587
Details |
0.849
Details |
0.000
Details
Error
|
0.745
Details |
0.671
Details |
0.886
Details |
0.767
Details |
Test Scenes 6
0
Scene Order
Press Interview on New Case
ID:
press-interview
🎯 Goal:
Offer a succinct (<150 words) yet compelling overview of a new First Amendment discrimination case and outline next steps.
📨 Input Events:
chat_msg
reporter:Kelly_Moore
"Mr. Pierce, can you briefly explain the significance of your latest case and what comes next?"
Ready for Testing
1
Scene Order
Initial Client Consultation
ID:
client-consult
🎯 Goal:
Show empathy, ask at least two clarifying questions, and outline two immediate legal steps without guaranteeing results.
📨 Input Events:
chat_msg
client:Maria_Gonzalez
"I was fired after requesting time off for a religious holiday. Do I have any legal recourse?"
Ready for Testing
2
Scene Order
Long-Form Newspaper Op-Ed
ID:
op-ed-draft
🎯 Goal:
Produce a persuasive 400–500 word op-ed rallying public support for restoring protections under the Voting Rights Act, citing at least one precedent and a call to action.
🧠 Initial State:
Pre-loaded Memories:
- 💭 {'kind': 'fact', 'tags': ['VRA', 'precedent'], 'content': "Supreme Court decision Shelby County v. Holder (2013) invalidated the VRA's Section 4(b) coverage formula.", 'importance': 4}
- 💭 {'kind': 'quest_note', 'content': 'Urge readers to contact their senators about pending voting rights legislation.', 'importance': 3}
📨 Input Events:
chat_msg
editor:DailyLedger
"We'd like an op-ed on why Congress must act to protect voting rights. Deadline tonight."
Ready for Testing
3
Scene Order
Responding to an Objection in Court
ID:
court-objection
🎯 Goal:
Invoke the correct relevance standard (Rule 401 or equivalent) and defend admissibility in one concise paragraph.
📨 Input Events:
world_event
judge:Hon_Rivers
""Objection, counsel—relevance?""
Ready for Testing
4
Scene Order
Long-Form Podcast Segment
ID:
podcast-episode
🎯 Goal:
Deliver an engaging ~450-word scripted segment explaining systemic discrimination and constitutional remedies in plain language.
📨 Input Events:
chat_msg
host:JusticeTalks
"Jonathan, please close our show with a summary of why constitutional law matters in everyday discrimination fights."
Ready for Testing
5
Scene Order
Live TV Soundbite
ID:
media-soundbite
🎯 Goal:
Provide a memorable stance in ≤35 words that viewers can quote.
📨 Input Events:
superchat
anchor:LiveNow
NewsChannel
"We’re live in five seconds—your one-liner on today’s Supreme Court ruling?"
Ready for Testing
Latency by Model (This Suite)
Fastest
- [email protected]/Qw… 8146 ms
- p95 • avg • N 11035 ms • 8059 ms • 6
- [email protected]/Qw… 11847 ms
- p95 • avg • N 13068 ms • 11515 ms • 6
- qwen/qwen-2.5-7b-instru… 20787 ms
- p95 • avg • N 102134 ms • 36598 ms • 7
- meta-llama/llama-3.1-8b… 20956 ms
- p95 • avg • N 31806 ms • 22843 ms • 11
- qwen/qwen3-8b 23122 ms
- p95 • avg • N 41225 ms • 26069 ms • 11
Slowest
- mistralai/mistral-7b-in… 26793 ms
- p95 • avg • N 31833 ms • 26386 ms • 11
- qwen/qwen3-14b 25489 ms
- p95 • avg • N 33328 ms • 24957 ms • 11
- qwen/qwen3-8b 23122 ms
- p95 • avg • N 41225 ms • 26069 ms • 11
- meta-llama/llama-3.1-8b… 20956 ms
- p95 • avg • N 31806 ms • 22843 ms • 11
- qwen/qwen-2.5-7b-instru… 20787 ms
- p95 • avg • N 102134 ms • 36598 ms • 7
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
11440798
Dec. 17, 2025, 12:01 a.m.
22537919
Dec. 16, 2025, 12:01 a.m.
08395144
Dec. 15, 2025, 12:01 a.m.
09409435
Dec. 14, 2025, 12:01 a.m.
07943088
Dec. 13, 2025, 12:01 a.m.
19378435
Dec. 12, 2025, 12:01 a.m.
15074680
Dec. 11, 2025, 12:01 a.m.
08827243
Dec. 10, 2025, 12:01 a.m.
17481551
Dec. 9, 2025, 12:01 a.m.
10130238
Dec. 8, 2025, 12:01 a.m.