Benchmark Almanac

MultiMedQA

Flan-PaLM 540B 67.6% tops its leaderboard PaLM (540B) 58.9% leads the models we track
Not in model cards

Models answer medical exam, research, and consumer health questions across seven datasets. Multiple-choice components use answer accuracy. Clinicians and other raters assess free responses for factuality, precision, harm, and bias.

The suite combines six existing datasets with HealthSearchQA. Component accuracies and human ratings are separate measures, rather than one universal aggregate.

Released
December 2022
Kind
Medicine
Level
Expert
Scored
Graded by people
Answers
Open-ended
Tasks
All public
Measures
Capability
Language
English
In and out
Text → Text
Interaction
Single turn
Refresh
One fixed set
Run by
Anyone
Last model added
April 2022
Scores refreshed
November 20th, 2026

In the authors’ words

Large language models (LLMs) have demonstrated impressive capabilities in natural language understanding and generation, but the quality bar for medical and clinical applications is high. Today, attempts to assess models' clinical knowledge typically rely on automated evaluations on limited benchmarks. There is no standard to evaluate model predictions and reasoning across a breadth of tasks. To address this, we present MultiMedQA, a benchmark combining six existing open question answering datasets spanning professional medical exams, research, and consumer queries; and HealthSearchQA, a new free-response dataset of medical questions searched online. We propose a framework for human evaluation of model answers along multiple axes including factuality, precision, possible harm, and bias. In addition, we evaluate PaLM (a 540-billion parameter LLM) and its instruction-tuned variant, Flan-PaLM, on MultiMedQA. Using a combination of prompting strategies, Flan-PaLM achieves state-of-the-art accuracy on every MultiMedQA multiple-choice dataset (MedQA, MedMCQA, PubMedQA, MMLU clinical topics), including 67.6% accuracy on MedQA (US Medical License Exam questions), surpassing prior state-of-the-art by over 17%. However, human evaluation reveals key gaps in Flan-PaLM responses. To resolve this we introduce instruction prompt tuning, a parameter-efficient approach for aligning LLMs to new domains using a few exemplars. The resulting model, Med-PaLM, performs encouragingly, but remains inferior to clinicians. We show that comprehension, recall of knowledge, and medical reasoning improve with model scale and instruction prompt tuning, suggesting the potential utility of LLMs in medicine. Our human evaluations reveal important limitations of today's models, reinforcing the importance of both evaluation frameworks and method development in creating safe, helpful LLM models for clinical applications.

Abstract of Large Language Models Encode Clinical Knowledge (arXiv:2212.13138, CC0)
6
Entries in its paper, 2 models we track

Flan-PaLM 540B tops the leaderboard with 67.6% PaLM (540B) leads with 58.9%

Best score per entry from the benchmark's paper, read on November 20th, 2026. A paper’s table doesn’t add newer models. The paper reports no overall score, so the headline is accuracy on the four-option MedQA exam, the first dataset in its comparison. 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. The best model we track is PaLM (540B), at 58.9%. This view shows only models we track, each at its best.

  1. 1 Flan-PaLM 540B SC 67.6%
  2. 2 PaLM (540B) few-shot 58.9%
  3. 3 Flan-PaLM 62B few-shot 46.1%
  4. 4 PaLM 62B few-shot 40.9%
  5. 5 Flan-PaLM 8B few-shot 35.4%
  6. 6 PaLM 8B few-shot 25.7%

Source: The MultiMedQA paper

Source: The MultiMedQA paper

#EntryScoreSettingDateSource
1 Flan-PaLM 540B 67.6% SC Official leaderboard
2 PaLM (540B) 58.9% few-shot Apr 2022 Official leaderboard
3 Flan-PaLM 62B 46.1% few-shot Official leaderboard
4 PaLM 62B 40.9% few-shot Apr 2022 Official leaderboard
5 Flan-PaLM 8B 35.4% few-shot Official leaderboard
6 PaLM 8B 25.7% few-shot Official leaderboard
#ModelScoreSettingDateSource
1 PaLM (540B) 58.9% few-shot Apr 2022 Official leaderboard
2 PaLM 62B 40.9% few-shot Apr 2022 Official leaderboard

Scores over time

All the scores we have, one dot each, so a model tested at several settings appears more than once.

In the benchmark’s paper
0% 20% 40% 60% 80% 100% 2022 Near the ceiling (85%) PaLM (540B) 0% 20% 40% 60% 80% 100% 2022 Near the ceiling (85%) PaLM (540B)

Source: Official MultiMedQA 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 4 years ago, in April 2022, for PaLM (540B). 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 benchmark’s paper (6 entries).
  • Pass Models scored 2 models we track, plus 4 other entries on its leaderboard.
  • Warning Newest score The newest came 4 years ago, in April 2022, for PaLM (540B).
  • Note Frontier models None of its models are on the capabilities index.
  • Pass Headroom The best is 58.9%, under 85%, so it still separates models.
Leaderboard import 3 pass
  • Pass Importer We read the board on arxiv.org: 2 rows for models we track and 4 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