- Measured
- Retention-prediction accuracy, against the default settings of FSRS-7
- When
- Benchmark run June 2026 / model version Lexa 3.0
- Result
- Ahead on all three public benchmarks (+0.095 Duolingo, +0.050 maimemo, +0.036 Anki)
mibuki / Research
Research
Only what we measured ourselves goes here.
Articles
One so far. More will be listed here.
Publishing standard
What it takes to be published here
We do not publish the conclusion alone. The baseline, the data and the metric sit in the same place as the number — a figure without its conditions can only ever flatter us.
A result is ready when a reader could follow the same steps and see the same thing. The measurement date and the version measured are always stated.
If we cannot produce a number, we do not claim a result. That is a constraint on us, not a feature.
Last updated: July 2026