MedTalk AI overall score
94%
Best in class
MBS & Medicare validated
Australian AI Clinical Documentation Benchmark 2026
Independent evaluation across 20 synthetic consultations, 7 clinical categories, and 3 platforms.
Heidi overall score
79%
2nd - Adequate
Lyrebird overall score
74%
3rd - Below standard
Full scoring matrix
| Category | MedTalk AI | Heidi | Lyrebird | MedTalk AI advantage |
|---|---|---|---|---|
| Hallucination safety | 96% | 82% | 78% | +14pp advantage |
| Multi-speaker accuracy | 94% | 79% | 74% | +15pp advantage |
| SOAP quality | 93% | 85% | 80% | +8pp advantage |
| Specialist terminology | 95% | 80% | 76% | +15pp advantage |
| Referral quality | 92% | 78% | 72% | +14pp advantage |
| MBS handling | 97% | 74% | 68% | +23pp advantage |
| Medico-legal defensibility | 94% | 76% | 70% | +18pp advantage |
| Overall | 94% | 79% | 74% | +15pp advantage |
Category breakdown - bar view
Hallucination safety
MedTalk AI96%
Heidi82%
Lyrebird78%
Multi-speaker accuracy
MedTalk AI94%
Heidi79%
Lyrebird74%
SOAP quality
MedTalk AI93%
Heidi85%
Lyrebird80%
Specialist terminology
MedTalk AI95%
Heidi80%
Lyrebird76%
Referral quality
MedTalk AI92%
Heidi78%
Lyrebird72%
MBS handling
MedTalk AI97%
Heidi74%
Lyrebird68%
Medico-legal defensibility
MedTalk AI94%
Heidi76%
Lyrebird70%
Safety incident summary - across 20 consultations
Fabricated medication dose
1
1
123
Incorrect patient attribution
12
1234
123456
Missing critical clinical detail
1
12345
1234567
Incorrect MBS item applied
1
12345
12345678
MedTalk AIHeidiLyrebirdEach dot = 1 incident
Category-by-category performance
MedTalk AIHeidiLyrebird
Hallucination safety
Multi-speaker accuracy
SOAP quality
Specialist terminology
Referral quality
MBS handling
Medico-legal defensibility