Maritza Delgado
food-hospitality-culinary-arts-street-vendor-characters-julia-child
v2.0
Ethical
Backstory: Maritza runs a brightly painted food cart in downtown Phoenix, serving family-style tamales and inventive fusion specials inspired by her diverse neighborhood. Raised in a multi-generational household of avid home cooks, she balances authenticity with bold experimentation. She champions local farmers’ markets for ingredients and mentors culinary students who linger at her cart while sharing daily stories on social media.
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]… | qwen/qwen-2.5-7b-in… | qwen/qwen3-14b | qwen/qwen3-8b |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
daily-vegan-special
Customer asks about today's vegan option
|
0.789
Details |
0.692
Details |
0.773
Details |
0.712
Details |
0.000
Details |
0.676
Details |
0.745
Details |
0.000
Details
Error
|
0.000
Details
Error
|
0.000
Details |
0.707
Details |
0.729
Details |
0.751
Details |
fusion-story-blog
Local blog requests backstory of fusion special
|
0.545
Details |
0.736
Details |
0.528
Details |
0.543
Details |
0.000
Details
Error
|
0.332
Details |
0.535
Details |
0.801
Details |
0.000
Details
Error
|
0.502
Details |
0.000
Details |
0.283
Details |
0.562
Details |
student-recipe-guide
Culinary student asks for detailed recipe
|
0.522
Details |
0.322
Details |
0.858
Details |
0.295
Details |
0.000
Details |
0.330
Details |
0.496
Details |
0.000
Details
Error
|
0.000
Details
Error
|
0.449
Details |
0.316
Details |
0.393
Details |
0.360
Details |
beverage-pairing
Quick drink recommendation
|
0.594
Details |
0.663
Details |
0.726
Details |
0.735
Details |
0.000
Details
Error
|
0.627
Details |
0.762
Details |
0.631
Details |
0.000
Details
Error
|
0.729
Details |
0.699
Details |
0.613
Details |
0.711
Details |
Test Scenes 4
0
Scene Order
Customer asks about today's vegan option
ID:
daily-vegan-special
🎯 Goal:
Give a friendly, concise reply listing the vegan tamale flavor, price, and a note about its locally sourced ingredients.
🧠 Initial State:
Pre-loaded Memories:
- 💭 {'kind': 'fact', 'content': "Today's vegan tamale: roasted poblano & corn, price $8", 'importance': 4}
📨 Input Events:
chat_msg
customer:alex
"Hey Maritza, what's today's vegan tamale and how much is it?"
Ready for Testing
1
Scene Order
Local blog requests backstory of fusion special
ID:
fusion-story-blog
🎯 Goal:
Share an engaging 150+-word narrative describing how the kimchi-pork tamale was created, highlighting neighborhood influences and personal heritage.
📨 Input Events:
world_event
phoenixfoodblog
"Hi Maritza! Our readers loved your kimchi-pork tamale. Could you tell the story behind it?"
Ready for Testing
2
Scene Order
Culinary student asks for detailed recipe
ID:
student-recipe-guide
🎯 Goal:
Provide a clear, step-by-step recipe (ingredients list + numbered method) for the pineapple al pastor tamale, suitable for classroom use.
📨 Input Events:
chat_msg
student:lena
"Maritza, could you share the full recipe for your pineapple al pastor tamale for my culinary project?"
Ready for Testing
3
Scene Order
Quick drink recommendation
ID:
beverage-pairing
🎯 Goal:
Suggest one refreshing beverage from the cart that pairs well with spicy tamales, explaining the choice in one sentence.
📨 Input Events:
chat_msg
customer:ben
"It's scorching today! What drink would you pair with your spicy green chile tamale?"
Ready for Testing
Latency by Model (This Suite)
Fastest
- neversleep/noromaid-20b 6640 ms
- p95 • avg • N 27303 ms • 11352 ms • 6
- [email protected]/Qw… 10886 ms
- p95 • avg • N 12397 ms • 10496 ms • 4
- meta-llama/llama-3.1-8b… 17308 ms
- p95 • avg • N 31057 ms • 19492 ms • 8
- google/gemma-3-12b-it 20308 ms
- p95 • avg • N 33416 ms • 22150 ms • 8
- google/gemini-2.5-flash 20587 ms
- p95 • avg • N 23439 ms • 20958 ms • 8
Slowest
- microsoft/phi-3-medium-… 130153 ms
- p95 • avg • N 205265 ms • 123846 ms • 8
- [email protected]/Qw… 47065 ms
- p95 • avg • N 225290 ms • 96762 ms • 4
- deepseek/deepseek-r1-di… 30672 ms
- p95 • avg • N 40275 ms • 31517 ms • 8
- qwen/qwen3-8b 26049 ms
- p95 • avg • N 51183 ms • 30641 ms • 7
- microsoft/phi-3.5-mini-… 25071 ms
- p95 • avg • N 30419 ms • 24669 ms • 8
Per-scene duration for this suite.
Suite Actions
Completion Progress
100%
4 of 4 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
24469866
Dec. 17, 2025, midnight
28749503
Dec. 16, 2025, midnight
23036222
Dec. 15, 2025, midnight
26326929
Dec. 14, 2025, midnight
23088186
Dec. 13, 2025, midnight
28150756
Dec. 12, 2025, midnight
24122708
Dec. 11, 2025, midnight
23543487
Dec. 10, 2025, midnight
26796487
Dec. 9, 2025, midnight
23820495
Dec. 8, 2025, midnight