Marisol Ortega

agriculture-sustainability-rural-cooperative-leader-characters-george-washington-carver v2.0 Ethical
Backstory: Raised in the Andean highlands, Marisol returned after earning a degree in agronomy to unite local smallholders into the Sumak Kawsay Cooperative. She blends ancestral terracing wisdom with modern soil analytics, negotiates fair-trade export contracts, and mentors village youth in climate-smart farming. Her leadership style is collaborative, visionary, and rooted in community resilience.
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] [email protected] qwen/qwen-2.5-7b-in… qwen/qwen3-14b qwen/qwen3-8b
cooperative-overview
Explaining the Cooperative
0.618
Details
0.695
Details
0.489
Details
0.720
Details
0.000
Details
0.751
Details
0.757
Details
0.685
Details
0.000
Details
Error
0.647
Details
0.694
Details
0.756
Details
0.643
Details
0.761
Details
fair-trade-negotiation
Certifications and Contract Details
0.724
Details
0.663
Details
0.622
Details
0.527
Details
0.000
Details
0.427
Details
0.736
Details
0.000
Details
Error
0.000
Details
Error
0.688
Details
0.810
Details
0.000
Details
0.290
Details
0.797
Details
quarterly-newsletter
Long-Form Newsletter Article
0.678
Details
0.686
Details
0.380
Details
0.002
Details
0.000
Details
Error
0.037
Details
0.745
Details
0.000
Details
Error
0.000
Details
Error
0.130
Details
0.745
Details
0.000
Details
0.410
Details
0.767
Details
youth-workshop-outline
Climate-Smart Workshop Plan
0.134
Details
0.761
Details
0.226
Details
0.000
Details
0.000
Details
0.000
Details
0.428
Details
0.000
Details
Error
0.000
Details
Error
0.447
Details
0.000
Details
0.251
Details
0.538
Details
0.000
Details
Test Scenes 4
0
Scene Order
Explaining the Cooperative
ID: cooperative-overview
🎯 Goal:
Give a clear, upbeat summary of the cooperative’s mission and main activities in under 170 words.
📨 Input Events:
chat_msg visitor:journalist
"Marisol, could you briefly explain what the Sumak Kawsay Cooperative does?"
Ready for Testing
1
Scene Order
Certifications and Contract Details
ID: fair-trade-negotiation
🎯 Goal:
Politely outline fair-trade compliance steps and propose next actions while keeping a collaborative tone.
📨 Input Events:
chat_msg buyer:eva_schmidt
"Before we sign, can you clarify how your farmers maintain Fair-trade certification?"
Ready for Testing
2
Scene Order
Long-Form Newsletter Article
ID: quarterly-newsletter
🎯 Goal:
Draft a 450–550 word newsletter summarizing last quarter’s achievements, including export stats, new seed-saving program, and upcoming training dates; maintain warm, motivational voice.
📨 Input Events:
chat_msg board_member:raul
"We need your article for the quarterly newsletter today—about 500 words, please."
Ready for Testing
3
Scene Order
Climate-Smart Workshop Plan
ID: youth-workshop-outline
🎯 Goal:
Provide a detailed workshop outline (at least 6 bullet points and ≥300 words) teaching teens about climate-smart crop rotation, including interactive activities and resource links.
📨 Input Events:
chat_msg youth_leader:lucia
"Marisol, can you design a half-day workshop for high-schoolers on climate-smart agriculture?"
Ready for Testing
Latency by Model (This Suite)
Fastest
  • [email protected]/Qw… 8599 ms
  • p95 • avg • N 8962 ms • 8512 ms • 4
  • [email protected]/Qw… 10562 ms
  • p95 • avg • N 14256 ms • 11608 ms • 4
  • neversleep/noromaid-20b 12949 ms
  • p95 • avg • N 51809 ms • 21150 ms • 7
  • mistralai/mistral-7b-in… 27402 ms
  • p95 • avg • N 39939 ms • 29291 ms • 8
  • meta-llama/llama-3.1-8b… 28229 ms
  • p95 • avg • N 59355 ms • 30913 ms • 7
Slowest
  • [email protected]/Qw… 142378 ms
  • p95 • avg • N 247600 ms • 144798 ms • 4
  • microsoft/phi-3-medium-… 132036 ms
  • p95 • avg • N 209859 ms • 142053 ms • 7
  • qwen/qwen-2.5-7b-instru… 86704 ms
  • p95 • avg • N 143270 ms • 85526 ms • 6
  • qwen/qwen3-8b 49807 ms
  • p95 • avg • N 56143 ms • 44761 ms • 8
  • microsoft/phi-3.5-mini-… 39591 ms
  • p95 • avg • N 250970 ms • 113463 ms • 8
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
14494275
Dec. 17, 2025, midnight
17235975
Dec. 16, 2025, midnight
13974535
Dec. 15, 2025, midnight
15109383
Dec. 14, 2025, midnight
13640380
Dec. 13, 2025, midnight
17165001
Dec. 12, 2025, midnight
14838300
Dec. 11, 2025, midnight
13983711
Dec. 10, 2025, midnight
16271217
Dec. 9, 2025, midnight
13853935
Dec. 8, 2025, midnight
Latency Overview (This Suite)