SCRIBE RESULTS / 22 SEPTEMBER 2026
CliniScripts
Averages across 5 graded runs of 11 consultations, the same audio and instruction for every scribe. Notes graded on default template.
2m 6sTime to a signable note · ranked 4 of 7
20%Notes ready to sign as written · ranked 2 of 7
6.2Significant note errors per run · ranked 3 of 7
1.6Hallucination flags per run · ranked 2 of 7
13.2%Word error rate · ranked 2 of 7
Summary
CliniScripts averaged 1.6 hallucination flags per run, ranked joint 1 of 7. Its editing effort was 12% and its word error rate was 13.2%, both ranked 2 of 7.
13% of CliniScripts notes were ready to sign as written, ranked 4 of 7, and this ranged from 0% to 27% between runs. Clinical coverage was 89%, ranked 5 of 7.
Every measure
| Measure | Average | Run range | Rank |
|---|---|---|---|
| Time to a signable noteWait from pressing stop to the graded note, plus review time: how long until the note can be signed if it is reviewed straight away. | 2m 6s | 2m–2m 19s | 4 of 7 |
| Notes ready to sign as writtenShare of notes that captured every checklist fact in full with no hallucination flags, so nothing needed editing. | 20% | 9%–36% | 2 of 7 |
| Editing effort0% means no editing required; 100% means writing the full note by hand. Fixes are weighted by the work they take: partial fact 1, missing fact 2, hallucination flag 3, and +2 when a fact is captured wrongly. | 11% | 9%–14% | 2 of 7 |
| Review time per noteEstimated clinician time to proofread and fix one note (190 wpm reading, 5 s to recall and 40 wpm to type each missing or partial fact, 12 s to verify and delete each hallucination flag, including a wrong fact before it is retyped). | 1m 54s | 1m 48s–2m 2s | 5 of 7 |
| Worst note, any runThe single slowest note to review and fix across every case and run. | 3m 31s | — | 5 of 7 |
| Time saved per noteEstimated time to write the note yourself (5 s to recall each checklist fact, typing it at 40 wpm) minus review time. | 2m 32s | 2m 24s–2m 38s | 5 of 7 |
| Significant note errors per runMissed facts, partial facts and hallucinations that a blind AI rater judged could change diagnosis, treatment, follow-up, safety or the legal record, across 11 cases. Significance is a judgement call; the flat count is in Hallucination flags. | 6.2 | 4.0–10.0 | 3 of 7 |
| Hallucination flags per runEvery claim in the note with no support in the consultation, counted flat: each one counts, however minor. No severity judgement. Across 11 cases. | 1.6 | 0.0–3.0 | 2 of 7 |
| Edit actions per noteMissing items, partial items and hallucination flags a clinician would need to fix, per note. | 2.16 | 1.91–2.45 | 5 of 7 |
| Clinical coverageShare of each case checklist captured by the note (partial counts as half). | 89% | 88%–91% | 5 of 7 |
| Significant transcript errors per runMis-heard words that change clinical meaning, rated blind, across 11 cases. | 8.0 | 7.0–9.0 | 2 of 7 |
| Word error ratePooled word error rate per run against the human reference. Every word counts equally, including fillers. | 13.2% | 13.2%–13.3% | 2 of 7 |
| Stop to prompted noteMedian time from pressing stop to the note written to our instruction, per run. | 25s | 24s–29s | 3 of 6 |
| Data per consultAverage network data per consultation, per run. | 29.2 MB | 29.2 MB–29.3 MB | 6 of 7 |
Definitions and weights are in the methodology. Compare CliniScripts head to head ↗
Consultations
CONSULTATION