Clinical SOAP Note Evaluation: Safety-First Benchmarking
Models turn 300 synthetic doctor-patient dialogues into clinical SOAP notes. Three judges check claims against transcript evidence and score numeric fidelity, coverage, and writing quality. The composite weights safety at 50%, coverage at 30%, and general quality at 20%.
The public article is dated April 17, 2026 and labels its data update December 14, 2025. The maker includes its own model. Synthetic dialogues and model judges do not establish clinical outcomes or validated documentation quality. This record covers the original six-model protocol, not AI Scribe Safety Benchmark v2.
- Made by
- Omi Health
- Released
- April 2026
- Kind
- Medicine
- Level
- Expert
- Scored
- Graded by a model
- Answers
- Open-ended
- Tasks
- All public
- Measures
- Capability
- Risk
- Specialized advice
- Subject
- Clinical medicine
- Language
- English
- Interaction
- Single turn
- Items from
- Generated
- Refresh
- One fixed set
- Run by
- Anyone
- In views
- Biology and medicine, Content safety
- Strongest model tested
- GPT-5.2 #51 on the capability index
- Last model added
- December 2025
- Scores refreshed
- November 18th, 2026
GPT-5.2 leads with 4.72 among models released by December 2025 GPT-5.2 leads with 4.72 among models released by December 2025
Best score per entry from the benchmark's own leaderboard, read on November 18th, 2026. Where a model ran with several settings or harnesses, we keep its best. Names in gray aren't in our model list: fine-tunes, agent systems, products and older models. They don't count toward leaders. This view shows only models we track, each at its best.
The newest model with a score here came out in December 2025, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:
- GPT-6.2 Astra
- Claude Fable 5.2
-
Gemini 4 Carbon
- GPT-6 Astra
- and 16 more
- 1 GPT-5.2 4.72
- 2
Gemini 3 Pro 4.70
- 3 Omi-SOAP-edge-v1 * 4.65
- 4 Kimi K2 Thinking 4.55
- 5 Claude Opus 4.5 4.54
- 6 GPT-5 4.29
Source: Official Clinical SOAP Note Evaluation: Safety-First Benchmarking leaderboard
- 1 GPT-5.2 4.72
- 2
Gemini 3 Pro 4.70
- 3 Kimi K2 Thinking 4.55
- 4 Claude Opus 4.5 4.54
- 5 GPT-5 4.29
Source: Official Clinical SOAP Note Evaluation: Safety-First Benchmarking leaderboard
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | GPT-5.2 | 4.72 | Dec 2025 | Official leaderboard | |
| 2 | | 4.70 | Nov 2025 | Official leaderboard | |
| 3 | Omi-SOAP-edge-v1 * | 4.65 | Official leaderboard | ||
| 4 | Kimi K2 Thinking | 4.55 | Nov 2025 | Official leaderboard | |
| 5 | Claude Opus 4.5 | 4.54 | Nov 2025 | Official leaderboard | |
| 6 | GPT-5 | 4.29 | Aug 2025 | Official leaderboard |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | GPT-5.2 | 4.72 | Dec 2025 | Official leaderboard | |
| 2 | | 4.70 | Nov 2025 | Official leaderboard | |
| 3 | Kimi K2 Thinking | 4.55 | Nov 2025 | Official leaderboard | |
| 4 | Claude Opus 4.5 | 4.54 | Nov 2025 | Official leaderboard | |
| 5 | GPT-5 | 4.29 | Aug 2025 | Official leaderboard |
Rankings by part
We read 4 parts from the benchmark’s own leaderboard, each ranking models on one part of the test, such as Safety, Coverage and Generalist. GPT-5.2 leads 3 of them, and Gemini 3 Pro leads the other one. Arrows show how far a model moved from its overall rank among the models we track.
Safety
5 models we track have a score here.
- 1 GPT-5.2 4.54
- 2
Gemini 3 Pro 4.54
- 3 Kimi K2 Thinking 4.22
- 4 Claude Opus 4.5 4.20
- 5 GPT-5 3.81
Coverage
5 models we track have a score here.
- 1 GPT-5.2 4.95
- 2 Claude Opus 4.5 ↑2 4.95
- 3 Kimi K2 Thinking 4.91
- 4
Gemini 3 Pro ↓2 4.86
- 5 GPT-5 4.84
Generalist
5 models we track have a score here.
- 1
Gemini 3 Pro ↑1 4.85
- 2 Kimi K2 Thinking ↑1 4.83
- 3 GPT-5.2 ↓2 4.82
- 4 Claude Opus 4.5 4.79
- 5 GPT-5 4.65
Evidence
Evidence accuracy supplies 70% of the safety dimension. 5 models we track have a score here.
- 1 GPT-5.2 4.36
- 2
Gemini 3 Pro 4.36
- 3 Kimi K2 Thinking 3.89
- 4 Claude Opus 4.5 3.87
- 5 GPT-5 3.32
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: Official Clinical SOAP Note Evaluation: Safety-First Benchmarking leaderboard
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: Official Clinical SOAP Note Evaluation: Safety-First Benchmarking leaderboard
No lab model card reports it yet
We read the headline results of 540 launch posts from 57 labs, and none of them list this benchmark.
More in Law, finance and medicine
- MedXpertQA-MM In use Models answer expert-level medical exam questions that combine images with clinical records and test results. Scoring is accuracy.
Qwen 3.8 Max 80.4%
- HealthBench Professional In use 525 physician-authored tasks from real clinician chats (care consult, documentation, research) with physician-adjudicated rubrics. Claude Sonnet 5.5 69.2%
- HealthBench In use 5,000 realistic health conversations graded against physician-written rubrics. A length-adjusted variant penalizes verbosity. GPT-5 67.2%
- FinSearchComp In use Agents search the web to fetch live financial data, look up history, and run multi-step investigations, across 635 expert-written questions. Scored by answer accuracy.
Ling-3.1-flash 81.7%
- KorMedMCQA In use Models answer 7,469 multiple-choice questions from Korean licensing exams for doctors, nurses, pharmacists and dentists, held from 2012 to 2024. o1-preview 92.7%
- Harvey LAB-AA v1.1 In use Artificial Analysis's run of Harvey's Legal Agent Benchmark on Harvey's newer private set of 120 tasks across 24 practice areas. A deliverable with a material hallucination scores zero, and the headline is the share of judges who find every rubric criterion passed. GPT-6.2 Astra 15%
Data audit
8 of 9 checks pass, 1 warning. Look first at the Newest score check. The newest came 11 months ago, in December 2025, for GPT-5.2. Every benchmark
Catalog record 2 pass
- Pass Task access All tasks are public.
- Pass Confidence Checked against a primary source.
Scores 1 warning 2 pass 2 notes
- Pass Independent runs Scores from the official leaderboard (6 entries).
- Pass Models scored 5 models we track, plus 1 other entry on its leaderboard.
- Warning Newest score The newest came 11 months ago, in December 2025, for GPT-5.2.
- Note Frontier models None of the top 10 has a score. The strongest tested is GPT-5.2 (#51).
- Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
- Pass Importer We read the board on omi.health: 5 rows for models we track and 1 other entry at the last read.
- Pass Last read November 18th, 2026.
- Pass Read worked The last read worked.
Consistency 1 pass 1 note
- Note Lab claims No model has both a lab number and an independent run.
- Pass Known issues No published audit found problems.