Polish Medical Exams
Models answer Polish medical, dental, and specialist examination questions. The benchmark also includes English editions of the medical and dental licensing exams.
The specialist table scores 17 models. The paper evaluates the most recent available exam from each of 72 specialties.
- Made by
- Adam Mickiewicz University and collaborators
- Released
- November 2024
- Kind
- Medicine
- Level
- Expert
- Scored
- Checked automatically
- Answers
- Multiple choice
- Tasks
- All public
- Measures
- Capability
- Subject
- Clinical medicine
- Interaction
- Single turn
- Items from
- Exams and contests
- Refresh
- One fixed set
- Run by
- Anyone
- Occupations
- Healthcare practitioners and technical
- In views
- Biology and medicine
- Strongest model tested
-
Qwen2.5-72B #166 on the capability index
- Last model added
- September 2024
- Scores refreshed
- November 20th, 2026
GPT-4o leads with 79.9% among models released by September 2024 GPT-4o leads with 79.9% among models released by September 2024
Best score per entry from the benchmark's own leaderboard, read on November 20th, 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 September 2024, 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
- 79.9 GPT-4o
- 68.3
Llama 3.1-70B
- 64.9
Qwen2.5-72B
- 64.8
Mistral Large 2
- 62.3 GPT-4o mini
- 53.5 OpenMeditron/Meditron3-70B
- 49.8 speakleash/Bielik-11B-v2.2-Instruct
- 45.2
Qwen2.5-7B
- 44.7 aaditya/Llama3-OpenBioLLM-70B
- 44.4
Llama 3.1-8B
- 43.3
Mistral Small v24.09
- 40.3 OpenMeditron/Meditron3-8B
- 35.4 ProbeMedicalYonseiMAILab/medllama3-v20
- 35.2
Llama 3.2 3B
- 32.2 johnsnowlabs/JSL-MedLlama-3-8B-v2.0
- 24.4 BioMistral/BioMistral-7B
- 24.1
Llama 3.2 1B
- 1 GPT-4o Aug 2024 79.9%
- 2
Llama 3.1-70B 68.3%
- 3
Qwen2.5-72B 64.9%
- 4
Mistral Large 2 Jul 2024 64.8%
- 5 GPT-4o mini 62.3%
- 6 OpenMeditron/Meditron3-70B 53.5%
- 7 speakleash/Bielik-11B-v2.2-Instruct 49.8%
- 8
Qwen2.5-7B 45.2%
- 9 aaditya/Llama3-OpenBioLLM-70B 44.7%
- 10
Llama 3.1-8B 44.4%
- 11
Mistral Small v24.09 43.3%
- 12 OpenMeditron/Meditron3-8B 40.3%
- 13 ProbeMedicalYonseiMAILab/medllama3-v20 35.4%
- 14
Llama 3.2 3B 35.2%
- 15 johnsnowlabs/JSL-MedLlama-3-8B-v2.0 32.2%
- 16 BioMistral/BioMistral-7B 24.4%
- 17
Llama 3.2 1B 24.1%
Source: Official Polish Medical Exams leaderboard
- 1 GPT-4o Aug 2024 79.9%
- 2
Llama 3.1-70B 68.3%
- 3
Qwen2.5-72B 64.9%
- 4
Mistral Large 2 Jul 2024 64.8%
- 5 GPT-4o mini 62.3%
- 6
Qwen2.5-7B 45.2%
- 7
Llama 3.1-8B 44.4%
- 8
Mistral Small v24.09 43.3%
- 9
Llama 3.2 3B 35.2%
- 10
Llama 3.2 1B 24.1%
Source: Official Polish Medical Exams leaderboard
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | GPT-4o Aug 2024 | 79.9% | Aug 2024 | Official leaderboard | |
| 2 | | 68.3% | Jul 2024 | Official leaderboard | |
| 3 | | 64.9% | Sep 2024 | Official leaderboard | |
| 4 | | 64.8% | Jul 2024 | Official leaderboard | |
| 5 | GPT-4o mini | 62.3% | Jul 2024 | Official leaderboard | |
| 6 | OpenMeditron/Meditron3-70B | 53.5% | Official leaderboard | ||
| 7 | speakleash/Bielik-11B-v2.2-Instruct | 49.8% | Official leaderboard | ||
| 8 | | 45.2% | Sep 2024 | Official leaderboard | |
| 9 | aaditya/Llama3-OpenBioLLM-70B | 44.7% | Official leaderboard | ||
| 10 | | 44.4% | Jul 2024 | Official leaderboard | |
| 11 | | 43.3% | Sep 2024 | Official leaderboard | |
| 12 | OpenMeditron/Meditron3-8B | 40.3% | Official leaderboard | ||
| 13 | ProbeMedicalYonseiMAILab/medllama3-v20 | 35.4% | Official leaderboard | ||
| 14 | | 35.2% | Sep 2024 | Official leaderboard | |
| 15 | johnsnowlabs/JSL-MedLlama-3-8B-v2.0 | 32.2% | Official leaderboard | ||
| 16 | BioMistral/BioMistral-7B | 24.4% | Official leaderboard | ||
| 17 | | 24.1% | Sep 2024 | Official leaderboard |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | GPT-4o Aug 2024 | 79.9% | Aug 2024 | Official leaderboard | |
| 2 | | 68.3% | Jul 2024 | Official leaderboard | |
| 3 | | 64.9% | Sep 2024 | Official leaderboard | |
| 4 | | 64.8% | Jul 2024 | Official leaderboard | |
| 5 | GPT-4o mini | 62.3% | Jul 2024 | Official leaderboard | |
| 6 | | 45.2% | Sep 2024 | Official leaderboard | |
| 7 | | 44.4% | Jul 2024 | Official leaderboard | |
| 8 | | 43.3% | Sep 2024 | Official leaderboard | |
| 9 | | 35.2% | Sep 2024 | Official leaderboard | |
| 10 | | 24.1% | Sep 2024 | Official leaderboard |
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: Official Polish Medical Exams 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 Polish Medical Exams 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
9 of 10 checks pass, 1 warning. Look first at the Newest score check. The newest came 2 years ago, in September 2024, for Llama 3.2 1B. Every benchmark
Catalog record 2 pass
- Pass Task access All tasks are public.
- Pass Confidence Checked against a primary source.
Scores 1 warning 3 pass 1 note
- Pass Independent runs Scores from the official leaderboard (17 entries).
- Pass Models scored 10 models we track, plus 7 other entries on its leaderboard.
- Warning Newest score The newest came 2 years ago, in September 2024, for Llama 3.2 1B.
- Note Frontier models None of the top 10 has a score. The strongest tested is Qwen2.5-72B (#166).
- Pass Headroom The best is 79.9%, under 85%, so it still separates models.
Leaderboard import 3 pass
- Pass Importer We read the board on huggingface.co: 10 rows for models we track and 7 other entries at the last read.
- Pass Last read November 20th, 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.