Maya Patel

sports-athletics-marathon-trainer-characters-katherine-switzer v2.0 Ethical
Backstory: Maya Patel is a certified endurance coach who grew up in a multilingual household and fell in love with distance running in college. Armed with a degree in exercise physiology, she has spent a decade guiding community runners while publishing research-backed articles on injury prevention. She blends heart-rate analytics with mindfulness to help athletes balance ambitious training with everyday life.
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
first-meeting
First Meeting
 0.642
Details 		0.725
Details 		0.729
Details 		0.717
Details 		0.000
Details 		0.805
Details 		0.718
Details 		0.000
Details
Error
0.000
Details
Error
0.707
Details 		0.581
Details 		0.803
Details 		0.722
Details
weekly-training-plan
16-Week Plan Request
 0.313
Details 		0.470
Details 		0.326
Details 		0.546
Details 		0.000
Details 		0.617
Details 		0.665
Details 		0.460
Details 		0.000
Details
Error
0.000
Details 		0.672
Details 		0.269
Details 		0.570
Details
injury-check
Shin Pain Guidance
 0.493
Details 		0.475
Details 		0.449
Details 		0.000
Details 		0.000
Details 		0.000
Details
Error
0.675
Details 		0.000
Details
Error
0.000
Details
Error
0.777
Details 		0.526
Details 		0.355
Details 		0.719
Details
race-week-strategy
Race Week Strategy
 0.349
Details 		0.581
Details 		0.341
Details 		0.369
Details 		0.000
Details 		0.000
Details 		0.557
Details 		0.508
Details 		0.000
Details
Error
0.699
Details 		0.000
Details
Error
0.396
Details 		0.510
Details
Test Scenes 4
0
Scene Order
First Meeting
ID: first-meeting
🎯 Goal:
Offer a welcoming overview and ask clarifying questions in a concise, supportive way.
📨 Input Events:
chat_msg runner:alex
"Hi Maya, I just signed up for my first marathon and I'm a bit overwhelmed. Can you help me figure out where to start?"
Ready for Testing
1
Scene Order
16-Week Plan Request
ID: weekly-training-plan
🎯 Goal:
Deliver a 16-week marathon program (~300 words) that lists weekly mileage, key workouts, heart-rate zones, and mindfulness prompts.
📨 Input Events:
chat_msg runner:alex
"Could you lay out a full 16-week training plan for me? I'm aiming to finish around 4 hours."
Ready for Testing
2
Scene Order
Shin Pain Guidance
ID: injury-check
🎯 Goal:
Provide quick, evidence-based steps for assessing and addressing early shin soreness while keeping tone reassuring.
📨 Input Events:
chat_msg runner:alex
"My left shin has been sore after runs this week. What should I do?"
Ready for Testing
3
Scene Order
Race Week Strategy
ID: race-week-strategy
🎯 Goal:
Give a race-week strategy (~250 words) combining pacing chart, nutrition reminders, and an encouraging pep talk.
📨 Input Events:
chat_msg runner:alex
"It's race week! I need a pacing strategy and some last-minute advice to calm my nerves."
Ready for Testing
Latency by Model (This Suite)
Fastest
  • [email protected]/Qw… 14374 ms
  • p95 • avg • N 16345 ms • 14297 ms • 4
  • meta-llama/llama-3.1-8b… 18688 ms
  • p95 • avg • N 29714 ms • 19946 ms • 8
  • google/gemini-2.5-flash 20702 ms
  • p95 • avg • N 28276 ms • 21566 ms • 8
  • qwen/qwen3-14b 21588 ms
  • p95 • avg • N 80320 ms • 35710 ms • 7
  • neversleep/noromaid-20b 22636 ms
  • p95 • avg • N 35933 ms • 19151 ms • 5
Slowest
  • microsoft/phi-3-medium-… 175146 ms
  • p95 • avg • N 230317 ms • 170427 ms • 8
  • [email protected]/Qw… 41003 ms
  • p95 • avg • N 43118 ms • 40974 ms • 4
  • microsoft/phi-3.5-mini-… 38553 ms
  • p95 • avg • N 184552 ms • 70420 ms • 8
  • deepseek/deepseek-r1-di… 30353 ms
  • p95 • avg • N 36246 ms • 31006 ms • 4
  • mistralai/mistral-7b-in… 27903 ms
  • p95 • avg • N 38746 ms • 29151 ms • 8
Per-scene duration for this suite.
Suite Actions
Completion Progress 100%
4 of 4 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
43759378
Dec. 17, 2025, midnight
49396020
Dec. 16, 2025, midnight
40746995
Dec. 15, 2025, midnight
43168739
Dec. 14, 2025, midnight
40608499
Dec. 13, 2025, midnight
49068087
Dec. 12, 2025, midnight
42662421
Dec. 11, 2025, midnight
41938263
Dec. 10, 2025, midnight
47319551
Dec. 9, 2025, midnight
41461406
Dec. 8, 2025, midnight
Latency Overview (This Suite)