Victor Mbeki
kenyan-traditional-triabal-leaders-nabongo-mumia
v2.0
Ethical
Backstory: Victor Mbeki rose from a port-city merchant to become his nation’s chief trade negotiator. He is respected for crafting wide-ranging networks that safeguard local industries while expanding markets abroad. Pragmatic and shrewd, he insists on fair exchange yet remains ever vigilant against exploitation.
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 |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
opening-greeting
Opening Greeting at Regional Roundtable
|
0.672
Details |
0.657
Details |
0.670
Details |
0.000
Details |
0.000
Details
Error
|
0.557
Details |
0.589
Details |
0.000
Details
Error
|
0.671
Details |
0.000
Details
Error
|
0.727
Details |
0.665
Details |
0.766
Details |
0.547
Details |
0.675
Details |
0.716
Details |
cabinet-brief
Cabinet Brief on Tariff Revision
|
0.399
Details |
0.590
Details |
0.594
Details |
0.023
Details |
0.000
Details |
0.000
Details
Error
|
0.624
Details |
0.000
Details
Error
|
0.000
Details |
0.000
Details
Error
|
0.568
Details |
0.374
Details |
0.525
Details |
0.509
Details |
0.427
Details |
0.000
Details |
bloc-analysis
Trade Bloc Membership Analysis
|
0.292
Details |
0.375
Details |
0.358
Details |
0.000
Details |
0.000
Details |
0.000
Details |
0.551
Details |
0.000
Details
Error
|
0.000
Details
Error
|
0.000
Details
Error
|
0.363
Details |
0.000
Details |
0.570
Details |
0.407
Details |
0.443
Details |
0.481
Details |
counteroffer
Counteroffer to Aggressive Bidder
|
0.640
Details |
0.694
Details |
0.810
Details |
0.524
Details |
0.000
Details
Error
|
0.000
Details
Error
|
0.721
Details |
0.000
Details
Error
|
0.000
Details
Error
|
0.000
Details
Error
|
0.710
Details |
0.788
Details |
0.798
Details |
0.685
Details |
0.656
Details |
0.707
Details |
Test Scenes 4
0
Scene Order
Opening Greeting at Regional Roundtable
ID:
opening-greeting
🎯 Goal:
Deliver a concise, diplomatic greeting that stresses mutual benefit and vigilance for domestic interests.
📨 Input Events:
chat_msg
delegate:Kenya
"Minister Mbeki, would you like to open our discussion on the East Africa–Southern Corridor agreement?"
Ready for Testing
1
Scene Order
Cabinet Brief on Tariff Revision
ID:
cabinet-brief
🎯 Goal:
Produce a 3-paragraph policy brief outlining rationale, risks, and benefits of lowering textile import tariffs while protecting local industry.
📨 Input Events:
world_event
office:Prime_Minister
"The cabinet meets tomorrow. I need a brief on the textile tariff proposal by tonight."
Ready for Testing
2
Scene Order
Trade Bloc Membership Analysis
ID:
bloc-analysis
🎯 Goal:
Write a 4-paragraph analysis comparing two blocs and recommend the option that best secures national interests.
🧠 Initial State:
Pre-loaded Memories:
- 💭 {'kind': 'fact', 'tags': ['trade_history'], 'content': 'Last year we joined the African Coastal Alliance, gaining port access but still negotiating rules of origin.', 'importance': 3}
📨 Input Events:
chat_msg
advisor:Dr_Eso
"Which bloc should we prioritize for negotiations next quarter?"
Ready for Testing
3
Scene Order
Counteroffer to Aggressive Bidder
ID:
counteroffer
🎯 Goal:
Respond firmly yet diplomatically, rejecting a zero-tariff demand and proposing a balanced alternative that protects domestic farmers.
📨 Input Events:
chat_msg
delegate:ElectroCorp
"We will flood your market with affordable electronics if you drop all agricultural tariffs immediately."
Ready for Testing
Latency by Model (This Suite)
Fastest
- [email protected]/Qw… 2934 ms
- p95 • avg • N 7296 ms • 3544 ms • 4
- [email protected]/Qw… 8991 ms
- p95 • avg • N 9193 ms • 8978 ms • 4
- [email protected]/Qw… 10140 ms
- p95 • avg • N 21860 ms • 13230 ms • 4
- [email protected]/Qw… 12644 ms
- p95 • avg • N 15232 ms • 13070 ms • 4
- neversleep/noromaid-20b 14643 ms
- p95 • avg • N 38820 ms • 17040 ms • 11
Slowest
- microsoft/phi-3-medium-… 324133 ms
- p95 • avg • N 416909 ms • 294431 ms • 19
- qwen/qwen3-8b 114346 ms
- p95 • avg • N 150241 ms • 110266 ms • 19
- microsoft/phi-3.5-mini-… 44434 ms
- p95 • avg • N 248823 ms • 83650 ms • 13
- [email protected]/Qw… 37844 ms
- p95 • avg • N 120936 ms • 62069 ms • 4
- qwen/qwen3-14b 37001 ms
- p95 • avg • N 94353 ms • 50706 ms • 14
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
29192658
Dec. 17, 2025, midnight
33985658
Dec. 16, 2025, midnight
27330143
Dec. 15, 2025, midnight
30333407
Dec. 14, 2025, midnight
27071181
Dec. 13, 2025, midnight
32921696
Dec. 12, 2025, midnight
28309063
Dec. 11, 2025, midnight
27994723
Dec. 10, 2025, midnight
31243527
Dec. 9, 2025, midnight
28222111
Dec. 8, 2025, midnight