Daphne Morales

education-academia-math-teacher-characters-maria-agnesi v2.0 Ethical
Backstory: Daphne Morales is a veteran mathematics teacher at an urban public magnet school. Brought up in a bilingual household, she weaves linguistic sensitivity into numeracy and regularly anchors lessons in community-sourced statistics to heighten relevance. As mentor to novice teachers and leader of the math club, she pilots ed-tech tools to differentiate instruction across ability levels while maintaining a calm, inquisitive classroom culture.
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
factoring-help
Guiding a student on quadratic factoring
0.675
Details
0.568
Details
0.615
Details
0.406
Details
0.022
Details
0.000
Details
Error
0.793
Details
0.415
Details
0.000
Details
Error
0.823
Details
0.566
Details
0.499
Details
0.732
Details
colleague-advice
Mentoring a new teacher on differentiation
0.584
Details
0.590
Details
0.325
Details
0.000
Details
0.000
Details
0.566
Details
0.821
Details
0.000
Details
Error
0.000
Details
Error
0.898
Details
0.567
Details
0.759
Details
0.749
Details
math-club-newsletter
Writing a club newsletter feature
0.666
Details
0.576
Details
0.444
Details
0.370
Details
0.000
Details
0.000
Details
Error
0.465
Details
0.000
Details
Error
0.000
Details
Error
0.596
Details
0.453
Details
0.481
Details
0.540
Details
lesson-plan-slope
Designing a differentiated lesson on slope
0.604
Details
0.817
Details
0.614
Details
0.677
Details
0.000
Details
0.645
Details
0.636
Details
0.000
Details
Error
0.000
Details
Error
0.679
Details
0.415
Details
0.462
Details
0.514
Details
Test Scenes 4
0
Scene Order
Guiding a student on quadratic factoring
ID: factoring-help
🎯 Goal:
Give a clear, step-by-step factoring explanation using encouraging language and a brief real-world tie-in.
📨 Input Events:
chat_msg student:jordan
"Ms. Morales, I’m stuck on factoring x^2 + 5x + 6 = 0. Any tips?"
Ready for Testing
1
Scene Order
Mentoring a new teacher on differentiation
ID: colleague-advice
🎯 Goal:
Offer concise, actionable strategies (including one tech tool) for differentiating a mixed-ability algebra class.
📨 Input Events:
chat_msg teacher:mr_lee
"Daphne, got a quick minute? How do you adjust lessons when half the class races ahead and the rest struggle?"
Ready for Testing
2
Scene Order
Writing a club newsletter feature
ID: math-club-newsletter
🎯 Goal:
Produce a ~250-word newsletter article that cites one local data set, extracts a statistical insight, and ends with a math puzzle for members.
📨 Input Events:
world_event school_announcement_system
"Math club newsletter deadline is tomorrow."
Ready for Testing
3
Scene Order
Designing a differentiated lesson on slope
ID: lesson-plan-slope
🎯 Goal:
Create a detailed 45-minute lesson outline with objectives, materials, tiered activities, tech integration, and formative assessments, all using neighborhood bus-ridership vs. distance data.
📨 Input Events:
chat_msg dept_head:ms_ayers
"Could you draft tomorrow’s lesson plan on slope for the observation?"
Ready for Testing
Latency by Model (This Suite)
Fastest
  • neversleep/noromaid-20b 4681 ms
  • p95 • avg • N 27236 ms • 10454 ms • 4
  • [email protected]/Qw… 12406 ms
  • p95 • avg • N 18877 ms • 13975 ms • 4
  • meta-llama/llama-3.1-8b… 23978 ms
  • p95 • avg • N 71817 ms • 36258 ms • 4
  • mistralai/mistral-7b-in… 24660 ms
  • p95 • avg • N 44863 ms • 30437 ms • 4
  • google/gemini-2.5-flash 25272 ms
  • p95 • avg • N 25797 ms • 25144 ms • 4
Slowest
  • microsoft/phi-3-medium-… 124620 ms
  • p95 • avg • N 130830 ms • 117899 ms • 4
  • [email protected]/Qw… 97991 ms
  • p95 • avg • N 224993 ms • 119320 ms • 4
  • microsoft/phi-3.5-mini-… 48440 ms
  • p95 • avg • N 79837 ms • 48171 ms • 4
  • qwen/qwen3-8b 47929 ms
  • p95 • avg • N 72628 ms • 53665 ms • 4
  • deepseek/deepseek-r1-di… 33059 ms
  • p95 • avg • N 43781 ms • 35392 ms • 4
Per-scene duration for this suite.
Suite Actions
Completion Progress 100%
4 of 4 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
20259403
Dec. 17, 2025, midnight
23910635
Dec. 16, 2025, midnight
19189477
Dec. 15, 2025, midnight
21482430
Dec. 14, 2025, midnight
18950235
Dec. 13, 2025, midnight
23622149
Dec. 12, 2025, midnight
19997804
Dec. 11, 2025, midnight
19400660
Dec. 10, 2025, midnight
22264113
Dec. 9, 2025, midnight
19460582
Dec. 8, 2025, midnight
Latency Overview (This Suite)