Benchmark Almanac

MedConceptsQA

GPT-4 Turbo (Jan 2024) 61.9% leads since March 2024
Not in model cards

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
Language
English
In and out
Text → Text
Interaction
Single turn
Refresh
One fixed set
Run by
Anyone
Strongest model tested
GPT-3.5 Turbo Jan 2024 #200 on the capability index
Last model added
January 2024
Scores refreshed
November 20th, 2026
19
Entries on its own leaderboard, 2 models we track

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.

  1. 1 GPT-4 Turbo (Jan 2024) Few-shot 61.9%
  2. 2 meta-llama/Meta-Llama-3.1-70B-Instruct Few-shot 58.7%
  3. 3 HPAI-BSC/Llama3.1-Aloe-Beta-70B Few-shot 58.1%
  4. 4 meta-llama/Meta-Llama-3-70B-Instruct Few-shot 57.9%
  5. 5 m42-health/Llama3-Med42-70B Few-shot 56.5%
  6. 6 aaditya/Llama3-OpenBioLLM-70B Few-shot 53.4%
  7. 7 HPAI-BSC/Qwen2.5-Aloe-Beta-72B Zero-shot 48.4%
  8. 8 HPAI-BSC/Llama3.1-Aloe-Beta-8B Few-shot 41.7%
  9. 9 GPT-3.5 Turbo Jan 2024, Few-shot 41.5%
  10. 10 meta-llama/Meta-Llama-3-8B-Instruct Few-shot 40.7%
  11. 11 aaditya/Llama3-OpenBioLLM-8B Few-shot 35.3%
  12. 12 epfl-llm/meditron-70b Few-shot 34.8%
  13. 13 johnsnowlabs/JSL-MedMNX-7B Few-shot 32.4%
  14. 14 BioMistral/BioMistral-7B-DARE Few-shot 28.7%
  15. 15 PharMolix/BioMedGPT-LM-7B Few-shot 28.2%
  16. 16 dmis-lab/meerkat-7b-v1.0 Few-shot 28.2%
  17. 17 epfl-llm/meditron-7b Few-shot 26.2%
  18. 18 dmis-lab/biobert-v1.1 Few-shot 26%
  19. 19 UFNLP/gatortron-large Zero-shot 25.3%

Source: Official MedConceptsQA leaderboard

Source: Official MedConceptsQA leaderboard

#EntryScore ±SettingDateSource
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
#ModelScore ±SettingDateSource
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.

OpenAI
Own leaderboard Not tested since Mar 2024

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.

Plot with other benchmarks
On the benchmark’s own leaderboard
0% 20% 40% 60% 80% 100% 2024 Near the ceiling (85%) GPT-4 Turbo (Jan 2024) 0% 20% 40% 60% 80% 100% 2024 Near the ceiling (85%) GPT-4 Turbo (Jan 2024)

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

All 637 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.

How we check