French–English consultation
Recording
Separate language cohort. Unsupported configurations are excluded. Freed translations/transliterations are not assigned comparable raw WER; Hindi remains a capability test.
| Platform | Review time | Time saved | Time to a signable note | Ready to sign as written | Editing effort | Significant note errors | Word error rate | Significant transcript errors | Full / partial / missing | Hallucination flags | Data | Stop to prompted note |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Hanah | ||||||||||||
| Heidi | ||||||||||||
| Freed | ||||||||||||
| CliniScripts | ||||||||||||
| 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.