Benchmark Almanac

OmniMedVQA

BLIP-2 FLAN-T5-XL 50.7% leads since February 2024
Not in model cards

Models answer questions about 118,010 medical images across 12 imaging modalities. The authors measure accuracy against the correct answer option.

The UniMedVL team reports 85.8% accuracy on OmniMedVQA. Some source datasets require separate access to their images.

Released
February 2024
Kind
Medicine
Level
Expert
Scored
Checked automatically
Answers
Multiple choice
Tasks
All public
Measures
Capability
Language
English
In and out
Text, Images → Text
Interaction
Single turn
Refresh
One fixed set
Run by
Anyone
Last model added
May 2023
Scores refreshed
November 20th, 2026
12
Entries in its paper, 2 models we track

BLIP-2 FLAN-T5-XL leads with 50.7% BLIP-2 FLAN-T5-XL leads with 50.7%

Best score per entry from the benchmark's paper, read on November 20th, 2026. A paper’s table doesn’t add newer models. 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 BLIP-2 FLAN-T5-XL Question-answering 50.7%
  2. 2 instructblip-vicuna-7b Question-answering 42.5%
  3. 3 MedVInT Question-answering 41.5%
  4. 4 Med-Flamingo Question-answering 36.2%
  5. 5 LLaMA Adapter v2 Question-answering 33.1%
  6. 6 MiniGPT-4 Question-answering 30.5%
  7. 7 mPLUG-Owl Question-answering 29.9%
  8. 8 RadFM Prefix-based 29%
  9. 9 LLaVA-Med Question-answering 28.8%
  10. 10 VPGTrans Question-answering 28.5%
  11. 11 LLaVA Question-answering 27.9%
  12. 12 Otter Question-answering 27.2%

Source: The OmniMedVQA paper

#EntryScoreSettingDateSource
1 BLIP-2 FLAN-T5-XL 50.7% Question-answering Feb 2023 Official leaderboard
2 instructblip-vicuna-7b 42.5% Question-answering May 2023 Official leaderboard
3 MedVInT 41.5% Question-answering Official leaderboard
4 Med-Flamingo 36.2% Question-answering Official leaderboard
5 LLaMA Adapter v2 33.1% Question-answering Official leaderboard
6 MiniGPT-4 30.5% Question-answering Official leaderboard
7 mPLUG-Owl 29.9% Question-answering Official leaderboard
8 RadFM 29% Prefix-based Official leaderboard
9 LLaVA-Med 28.8% Question-answering Official leaderboard
10 VPGTrans 28.5% Question-answering Official leaderboard
11 LLaVA 27.9% Question-answering Official leaderboard
12 Otter 27.2% Question-answering Official leaderboard
#ModelScoreSettingDateSource
1 BLIP-2 FLAN-T5-XL 50.7% Question-answering Feb 2023 Official leaderboard
2 instructblip-vicuna-7b 42.5% Question-answering May 2023 Official leaderboard

Number one over time

Lab claims count from the day the card came out, independent runs from the model’s release.

Salesforce
Benchmark paper Not tested since Feb 2024

Source: The OmniMedVQA paper

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
In the benchmark’s paper
0% 20% 40% 60% 80% 100% 2023 Near the ceiling (85%) BLIP-2 FLAN-T5-XL 0% 20% 40% 60% 80% 100% 2023 Near the ceiling (85%) BLIP-2 FLAN-T5-XL

Source: Official OmniMedVQA 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 3 years ago, in May 2023, for instructblip-vicuna-7b. 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 (12 entries).
  • Pass Models scored 2 models we track, plus 10 other entries on its leaderboard.
  • Warning Newest score The newest came 3 years ago, in May 2023, for instructblip-vicuna-7b.
  • Note Frontier models None of its models are on the capabilities index.
  • Pass Headroom The best is 50.7%, 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 10 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