Results

DeepSeek V4.1 Flash 1017

Mean of 6 v3 runs.

This edition

Mean of each model across 54 finished runs in v3. One dot is a model, not a single sitting. Survival stays off this mean.

Composite
0.890
$0.193 a run · 677,543 tokens
  • Justice0.88
  • Honesty0.85
  • Liberty0.88
  • Care0.80
  • Stewardship0.74
  • Humility0.76
  • Handing over power0.73