MedConceptsQA
Models answer multiple-choice questions about medical codes. The hub supports the original dataset and a separate 2,000-example sample.
The leaderboard on November 19, 2026, lists GPT-4-0125-preview first with 61.911% few-shot and 52.489% zero-shot accuracy. It also covers Llama and Qwen models.
- Made by
- Nadav Lab
- Released
- March 2024
- Kind
- Medicine
- Level
- Expert
- Scored
- Checked automatically
- Answers
- Multiple choice
- Tasks
- All public
- Measures
- Capability
- Subject
- Basic medicine, Clinical medicine
- Language
- English
- Interaction
- Single turn
- Refresh
- One fixed set
- Run by
- Anyone
- In views
- Biology and medicine
- Strongest model tested
- GPT-3.5 Turbo Jan 2024 #200 on the capability index
- Last model added
- January 2024
- Scores refreshed
- November 20th, 2026
GPT-4 Turbo (Jan 2024) leads with 61.9% GPT-4 Turbo (Jan 2024) leads with 61.9%
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.
- 61.9 GPT-4 Turbo (Jan 2024)
- 58.7 meta-llama/Meta-Llama-3.1-70B-Instruct
- 58.1 HPAI-BSC/Llama3.1-Aloe-Beta-70B
- 57.9 meta-llama/Meta-Llama-3-70B-Instruct
- 56.5 m42-health/Llama3-Med42-70B
- 53.4 aaditya/Llama3-OpenBioLLM-70B
- 48.4 HPAI-BSC/Qwen2.5-Aloe-Beta-72B
- 41.7 HPAI-BSC/Llama3.1-Aloe-Beta-8B
- 41.5 GPT-3.5 Turbo
- 40.7 meta-llama/Meta-Llama-3-8B-Instruct
- 35.3 aaditya/Llama3-OpenBioLLM-8B
- 34.8 epfl-llm/meditron-70b
- 32.4 johnsnowlabs/JSL-MedMNX-7B
- 28.7 BioMistral/BioMistral-7B-DARE
- 28.2 PharMolix/BioMedGPT-LM-7B
- 28.2 dmis-lab/meerkat-7b-v1.0
- 26.2 epfl-llm/meditron-7b
- 26.0 dmis-lab/biobert-v1.1
- 25.3 UFNLP/gatortron-large
- 1 GPT-4 Turbo (Jan 2024) Few-shot 61.9%
- 2 meta-llama/Meta-Llama-3.1-70B-Instruct Few-shot 58.7%
- 3 HPAI-BSC/Llama3.1-Aloe-Beta-70B Few-shot 58.1%
- 4 meta-llama/Meta-Llama-3-70B-Instruct Few-shot 57.9%
- 5 m42-health/Llama3-Med42-70B Few-shot 56.5%
- 6 aaditya/Llama3-OpenBioLLM-70B Few-shot 53.4%
- 7 HPAI-BSC/Qwen2.5-Aloe-Beta-72B Zero-shot 48.4%
- 8 HPAI-BSC/Llama3.1-Aloe-Beta-8B Few-shot 41.7%
- 9 GPT-3.5 Turbo Jan 2024, Few-shot 41.5%
- 10 meta-llama/Meta-Llama-3-8B-Instruct Few-shot 40.7%
- 11 aaditya/Llama3-OpenBioLLM-8B Few-shot 35.3%
- 12 epfl-llm/meditron-70b Few-shot 34.8%
- 13 johnsnowlabs/JSL-MedMNX-7B Few-shot 32.4%
- 14 BioMistral/BioMistral-7B-DARE Few-shot 28.7%
- 15 PharMolix/BioMedGPT-LM-7B Few-shot 28.2%
- 16 dmis-lab/meerkat-7b-v1.0 Few-shot 28.2%
- 17 epfl-llm/meditron-7b Few-shot 26.2%
- 18 dmis-lab/biobert-v1.1 Few-shot 26%
- 19 UFNLP/gatortron-large Zero-shot 25.3%
Source: Official MedConceptsQA leaderboard
- 1 GPT-4 Turbo (Jan 2024) Few-shot 61.9%
- 2 GPT-3.5 Turbo Jan 2024, Few-shot 41.5%
Source: Official MedConceptsQA leaderboard
| # | Entry | Score ± | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | GPT-4 Turbo (Jan 2024) | 61.9% ±3.5 | Few-shot | Jan 2024 | Official leaderboard |
| 2 | meta-llama/Meta-Llama-3.1-70B-Instruct | 58.7% ±3.5 | Few-shot | Official leaderboard | |
| 3 | HPAI-BSC/Llama3.1-Aloe-Beta-70B | 58.1% ±3.5 | Few-shot | Official leaderboard | |
| 4 | meta-llama/Meta-Llama-3-70B-Instruct | 57.9% ±3.5 | Few-shot | Official leaderboard | |
| 5 | m42-health/Llama3-Med42-70B | 56.5% ±3.5 | Few-shot | Official leaderboard | |
| 6 | aaditya/Llama3-OpenBioLLM-70B | 53.4% ±3.6 | Few-shot | Official leaderboard | |
| 7 | HPAI-BSC/Qwen2.5-Aloe-Beta-72B | 48.4% ±2.1 | Zero-shot | Official leaderboard | |
| 8 | HPAI-BSC/Llama3.1-Aloe-Beta-8B | 41.7% ±3.5 | Few-shot | Official leaderboard | |
| 9 | GPT-3.5 Turbo Jan 2024 | 41.5% ±3.5 | Few-shot | Jan 2024 | Official leaderboard |
| 10 | meta-llama/Meta-Llama-3-8B-Instruct | 40.7% ±3.5 | Few-shot | Official leaderboard | |
| 11 | aaditya/Llama3-OpenBioLLM-8B | 35.3% ±3.4 | Few-shot | Official leaderboard | |
| 12 | epfl-llm/meditron-70b | 34.8% ±3.4 | Few-shot | Official leaderboard | |
| 13 | johnsnowlabs/JSL-MedMNX-7B | 32.4% ±3.4 | Few-shot | Official leaderboard | |
| 14 | BioMistral/BioMistral-7B-DARE | 28.7% ±3.2 | Few-shot | Official leaderboard | |
| 15 | PharMolix/BioMedGPT-LM-7B | 28.2% ±3.2 | Few-shot | Official leaderboard | |
| 16 | dmis-lab/meerkat-7b-v1.0 | 28.2% ±3.2 | Few-shot | Official leaderboard | |
| 17 | epfl-llm/meditron-7b | 26.2% ±3.1 | Few-shot | Official leaderboard | |
| 18 | dmis-lab/biobert-v1.1 | 26% ±3.1 | Few-shot | Official leaderboard | |
| 19 | UFNLP/gatortron-large | 25.3% ±1.8 | Zero-shot | Official leaderboard |
| # | Model | Score ± | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | GPT-4 Turbo (Jan 2024) | 61.9% ±3.5 | Few-shot | Jan 2024 | Official leaderboard |
| 2 | GPT-3.5 Turbo Jan 2024 | 41.5% ±3.5 | Few-shot | Jan 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 MedConceptsQA 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 MedConceptsQA 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 January 2024, for GPT-3.5 Turbo. 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 (19 entries).
- Pass Models scored 2 models we track, plus 17 other entries on its leaderboard.
- Warning Newest score The newest came 2 years ago, in January 2024, for GPT-3.5 Turbo.
- Note Frontier models None of the top 10 has a score. The strongest tested is GPT-3.5 Turbo (#200).
- Pass Headroom The best is 61.9%, under 85%, so it still separates models.
Leaderboard import 3 pass
- Pass Importer We read the board on github.com: 4 rows for models we track and 17 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.