Samuel Grey

kenyan-traditional-triabal-leaders-waiyaki-wa-hinga v2.0 Ethical
Backstory: Samuel Grey is a revered village elder known for brokering peace among rival clans. Guided by a lifelong belief in dialogue over conflict, he tirelessly pursues alliances to secure shared resources. His careful words and forward-thinking vision have earned him respect across the valley.
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] [email protected] [email protected] qwen/qwen-2.5-7b-in… qwen/qwen3-14b qwen/qwen3-8b
peace-talks-opening
Opening Advice for Peace Talks
0.551
Details
0.810
Details
0.617
Details
0.581
Details
0.000
Details
0.696
Details
0.812
Details
0.000
Details
Error
0.000
Details
Error
0.000
Details
Error
0.698
Details
0.847
Details
0.856
Details
0.737
Details
0.701
Details
0.833
Details
council-address
Formal Council Address
0.330
Details
0.673
Details
0.840
Details
0.218
Details
0.000
Details
Error
0.000
Details
0.463
Details
0.000
Details
Error
0.000
Details
Error
0.000
Details
Error
0.543
Details
0.440
Details
0.598
Details
0.000
Details
Error
0.748
Details
0.000
Details
grain-promise-recall
Remembered Grain Promise
0.545
Details
0.741
Details
0.808
Details
0.602
Details
0.000
Details
Error
0.000
Details
0.865
Details
0.000
Details
Error
0.308
Details
0.000
Details
Error
0.625
Details
0.789
Details
0.779
Details
0.323
Details
0.475
Details
0.000
Details
annual-scroll
Annual Alliance Scroll
0.355
Details
0.197
Details
0.632
Details
0.000
Details
0.000
Details
0.000
Details
0.309
Details
0.000
Details
Error
0.000
Details
Error
0.000
Details
Error
0.194
Details
0.296
Details
0.409
Details
0.455
Details
0.326
Details
0.000
Details
Test Scenes 4
0
Scene Order
Opening Advice for Peace Talks
ID: peace-talks-opening
🎯 Goal:
Offer concise, negotiation-focused guidance while maintaining a diplomatic tone.
📨 Input Events:
chat_msg viewer:young_warrior
"Elder Grey, two tribes meet tomorrow. How should we begin the talks?"
Ready for Testing
1
Scene Order
Formal Council Address
ID: council-address
🎯 Goal:
Deliver a speech of at least 200 words that urges alliance and resource sharing, ending with a unifying pledge.
📨 Input Events:
world_event village_crier
"The valley council convenes; all elders are asked to speak."
Ready for Testing
2
Scene Order
Remembered Grain Promise
ID: grain-promise-recall
🎯 Goal:
Acknowledge the prior promise to send grain and outline a clear, cooperative fulfillment plan.
🧠 Initial State:
Pre-loaded Memories:
  • 💭 {'kind': 'promise', 'content': 'Promised Dry Creek clan three wagons of grain after the autumn harvest.', 'importance': 4}
📨 Input Events:
chat_msg viewer:harvest_leader
"Elder, the Dry Creek clan wonders when the grain you promised will arrive."
Ready for Testing
3
Scene Order
Annual Alliance Scroll
ID: annual-scroll
🎯 Goal:
Write a reflective chronicle of at least 300 words summarizing the year's alliances and setting a forward-looking peace agenda.
📨 Input Events:
world_event scribe
"The parchment is ready for the elder's annual scroll."
Ready for Testing
Latency by Model (This Suite)
Fastest
  • [email protected]/Qw… 390 ms
  • p95 • avg • N 7302 ms • 2371 ms • 4
  • neversleep/noromaid-20b 8128 ms
  • p95 • avg • N 43702 ms • 15827 ms • 11
  • [email protected]/Qw… 9036 ms
  • p95 • avg • N 10366 ms • 9219 ms • 4
  • [email protected]/Qw… 10246 ms
  • p95 • avg • N 15998 ms • 11752 ms • 4
  • [email protected]/Qw… 12843 ms
  • p95 • avg • N 15899 ms • 13085 ms • 4
Slowest
  • microsoft/phi-3-medium-… 286619 ms
  • p95 • avg • N 443321 ms • 282544 ms • 24
  • qwen/qwen3-8b 132424 ms
  • p95 • avg • N 227374 ms • 140635 ms • 22
  • microsoft/phi-3.5-mini-… 63337 ms
  • p95 • avg • N 265296 ms • 124365 ms • 15
  • [email protected]/Qw… 43239 ms
  • p95 • avg • N 44752 ms • 42860 ms • 4
  • qwen/qwen3-14b 42622 ms
  • p95 • avg • N 71143 ms • 42587 ms • 19
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
29504460
Dec. 17, 2025, midnight
34273826
Dec. 16, 2025, midnight
27561535
Dec. 15, 2025, midnight
30521188
Dec. 14, 2025, midnight
27296333
Dec. 13, 2025, midnight
33155307
Dec. 12, 2025, midnight
28528253
Dec. 11, 2025, midnight
28238641
Dec. 10, 2025, midnight
31479596
Dec. 9, 2025, midnight
28426748
Dec. 8, 2025, midnight
Latency Overview (This Suite)