50-minute stress test
Local preview — Hanah notes regenerated on 11 October 2026 with GPT-6.1 Sol, low reasoning: 50 notes across 10 consultations, five stored transcript variants each. Two consultations await new Hanah notes. WER and transcription evidence retain their original capture dates; other scribes retain their existing results. New notes were graded blind by Sonnet 5.5 medium, followed by an unblinded agent audit; provisional, without independent clinician validation. Hanah timings are estimates: prompted-note wait uses measured API generation duration + 2 seconds readiness allowance; time to a finalised note adds estimated review and correction time. Both exclude transcription finalisation and app overhead, pending a live rerun.
Recording
| Platform | Review time | Time saved | Time to a finalised note | Ready to finalise as written | Faster than writing it yourself | Editing effort | Note errors (Weiner et al. standard) | Word error rate | Significant transcript errors | Clinical coverage | Hallucination flags | Data | Stop to prompted note |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Hanah | |||||||||||||
| Heidi | |||||||||||||
| Freed | |||||||||||||
| CliniScripts | |||||||||||||
| Lyrebird | |||||||||||||
| PatientNotes |
Each figure is the average across every graded run of this consultation; the small line is the range. Best is the lowest average (highest coverage). How these measures work →
Download every run for this consultation: CSV · JSON with transcripts, notes and jury reasons · everything, every consultation (JSON)
Face-off
Pick two scribes
Each rope is pulled toward the scribe that did better on that measure. The further the ribbon moves from the centre line, the bigger the gap. The shaded band is where it would land between each scribe’s best and worst run: a wide band means inconsistent results. Small figures are the run range.