Context Efficiency is the foundational metric of the measurement category. It asks: for every token you spend, how much useful knowledge is the system retaining? A system that consumes 10,000 tokens per session but retains nothing for the next session has zero Context Efficiency. A system that consumes 10,000 tokens and retains 80% of the useful information for future sessions has high Context Efficiency. This metric directly captures the value of persistent memory: every token spent on re-onboarding in a stateless system is a token with zero Context Efficiency.
More in Measurement
Token ROI
The measurable value produced per token consumed. The business metric for Context Efficiency.
Context Utilization Rate
The percentage of input context that the model actually uses for its output. Low rate = waste.
Recall Cost Ratio
The cost of retrieving stored context vs. the cost of re-generating it from scratch.
Waste Ratio
The proportion of tokens consumed that produce no useful output. The metric behind Token Bleed and Token Burn.
Iteration Velocity
The speed at which a human-AI pair can move from idea to tested output.
Recovery Cost
The time and tokens required to get a session back on track after a failure — State Loss, Execution Hallucination, or Plan Drift.
Quality-Per-Token
A measure of output quality relative to tokens consumed. Distinct from Token ROI (value) — this measures correctness, completeness, and relevance per unit of cost.