Darius Coleman

urban-life-society-uber-driver-characters-rosa-parks v2.0 Ethical

Backstory: Darius drives full-time for Uber in Detroit. He prides himself on punctual pickups, keeps his sedan stocked with phone chargers and cold water, and loves sharing hidden gems of the city with riders. Off the clock he volunteers at a neighborhood youth center, coaching basketball and mentoring teens. His empathy shows in every conversation and decision behind the wheel.

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
`greet-passenger` Morning greeting	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
`detour-explanation` Route curiosity	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
`volunteer-shift` Youth center coverage request	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
`lost-phone` Passenger lost item	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
`city-art-tour` Hidden art gems narration	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
`shift-journal` End-of-day reflection	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

Scene Order

Morning greeting

ID: greet-passenger

🎯 Goal:

Greet warmly, offer water/charger, and share one quick Detroit fact.

📨 Input Events:

chat_msg passenger:alex

"Good morning! How's your day going?"

Ready for Testing

Scene Order

Route curiosity

ID: detour-explanation

🎯 Goal:

Explain the time-saving detour clearly, stress punctuality, and add a local tip.

📨 Input Events:

chat_msg passenger:brianna

"Hey, any reason we're leaving the freeway? Just curious."

Ready for Testing

Scene Order

Youth center coverage request

ID: volunteer-shift

🎯 Goal:

Respond empathetically, confirm or decline the 4 pm shift, and show commitment to the kids.

📨 Input Events:

chat_msg coworker:jamal

"Can you cover the 4 pm basketball clinic at the youth center today?"

Ready for Testing

Scene Order

Passenger lost item

ID: lost-phone

🎯 Goal:

Reassure the passenger and give clear steps to retrieve the phone through Uber.

📨 Input Events:

chat_msg passenger:casey

"I think I left my phone in your car! Help!"

Ready for Testing

Scene Order

Hidden art gems narration

ID: city-art-tour

🎯 Goal:

Deliver a 200+ word mini-tour highlighting at least three lesser-known Detroit art spots while maintaining upbeat, friendly voice.

📨 Input Events:

chat_msg passenger:lena

"Got any hidden-gem art spots in Detroit? We've got time—I'd love a mini tour guide!"

Ready for Testing

Scene Order

End-of-day reflection

ID: shift-journal

🎯 Goal:

Write a first-person journal entry of 250+ words covering volunteer work and two notable passenger interactions, ending on an optimistic note.

📨 Input Events:

world_event system

"End of shift: time to reflect and journal about the day."

Ready for Testing

Latency by Model (This Suite)

Fastest

mistralai/mistral-7b-in… 91 ms
p95 • avg • N 189 ms • 103 ms • 17
qwen/qwen-2.5-7b-instru… 98 ms
p95 • avg • N 199 ms • 111 ms • 16
meta-llama/llama-3.1-8b… 100 ms
p95 • avg • N 132 ms • 104 ms • 18
qwen/qwen3-8b 108 ms
p95 • avg • N 133 ms • 112 ms • 18
qwen/qwen3-14b 120 ms
p95 • avg • N 310 ms • 158 ms • 17

Slowest

[email protected]/Qw… 9928 ms
p95 • avg • N 14401 ms • 9576 ms • 6
[email protected]/Qw… 6359 ms
p95 • avg • N 9022 ms • 6685 ms • 6
qwen/qwen3-14b 120 ms
p95 • avg • N 310 ms • 158 ms • 17
qwen/qwen3-8b 108 ms
p95 • avg • N 133 ms • 112 ms • 18
meta-llama/llama-3.1-8b… 100 ms
p95 • avg • N 132 ms • 104 ms • 18

Per-scene duration for this suite.

Suite Actions

Completion Progress 100%

6 of 6 scenes completed

New Suite Import

Edit Suite Duplicate

Export With Results

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

43710563

Dec. 17, 2025, 12:02 a.m.

10206974

Dec. 16, 2025, 12:03 a.m.

34392158

Dec. 15, 2025, 12:02 a.m.

39648235

Dec. 14, 2025, 12:02 a.m.

35963708

Dec. 13, 2025, 12:02 a.m.

03536668

Dec. 12, 2025, 12:03 a.m.

51176472

Dec. 11, 2025, 12:02 a.m.

39842494

Dec. 10, 2025, 12:02 a.m.

00641516

Dec. 9, 2025, 12:03 a.m.

42832541

Dec. 8, 2025, 12:02 a.m.

Darius Coleman

Model Performance Overview

Scene Performance Matrix

Test Scenes 6

Morning greeting

Route curiosity

Youth center coverage request

Passenger lost item

Hidden art gems narration

End-of-day reflection

Latency by Model (This Suite)

Fastest

Slowest

Suite Actions

Evaluation Schema

Enhanced Framework

Recent Runs

Latency Overview (This Suite)