Benchmark Almanac

MedHEB

MedEmb-8B 49.3 tops its leaderboard Qwen3-VL-Embedding-8B 24.6 leads the models we track
Not in model cards

Models retrieve related medical images, reports, and image regions. The authors evaluate how models rank relevant evidence across 107 retrieval tasks.

Made by
Yingshu Li and colleagues
Released
November 2026
Kind
Medicine
Level
University
Scored
Checked automatically
Answers
Short answer
Tasks
All public
Measures
Capability
Language
English
In and out
Text, Images, 3D → Text, Images, 3D
Interaction
Single turn
Items from
Real work and use
Refresh
One fixed set
Run by
Anyone
Last model added
January 2026
Scores refreshed
November 20th, 2026
10
Entries in its paper, 2 models we track

MedEmb-8B tops the leaderboard with 49.3 Qwen3-VL-Embedding-8B leads with 24.6

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. The best model we track is Qwen3-VL-Embedding-8B, at 24.6. This view shows only models we track, each at its best.

  1. 1 MedEmb-8B 49.3
  2. 2 MedEmb-2B 45.6
  3. 3 Qwen3-VL-Embedding-8B 24.6
  4. 4 Qwen3-VL-Embedding-2B 22.5
  5. 5 MedImageInsight 21.8
  6. 6 RzenEmbed 18.5
  7. 7 VLM2Vec-V2.0 16.9
  8. 8 SigLIP 14.9
  9. 9 MedSigLIP 13.8
  10. 10 BLIP-2 11.8

Source: The MedHEB paper

#EntryScoreSettingDateSource
1 MedEmb-8B 49.3 Official leaderboard
2 MedEmb-2B 45.6 Official leaderboard
3 Qwen3-VL-Embedding-8B 24.6 Jan 2026 Official leaderboard
4 Qwen3-VL-Embedding-2B 22.5 Jan 2026 Official leaderboard
5 MedImageInsight 21.8 Official leaderboard
6 RzenEmbed 18.5 Official leaderboard
7 VLM2Vec-V2.0 16.9 Official leaderboard
8 SigLIP 14.9 Official leaderboard
9 MedSigLIP 13.8 Official leaderboard
10 BLIP-2 11.8 Official leaderboard
#ModelScoreSettingDateSource
1 Qwen3-VL-Embedding-8B 24.6 Jan 2026 Official leaderboard
2 Qwen3-VL-Embedding-2B 22.5 Jan 2026 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
22.0 23.0 24.0 25.0 2026 22.0 23.0 24.0 25.0 2026

Source: Official MedHEB 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

8 of 9 checks pass, 1 warning. Look first at the Newest score check. The newest came 10 months ago, in January 2026, for Qwen3-VL-Embedding-2B. Every benchmark

Catalog record 2 pass
  • Pass Task access All tasks are public.
  • Pass Confidence Checked against a primary source.
Scores 1 warning 2 pass 2 notes
  • Pass Independent runs Scores from the benchmark’s paper (10 entries).
  • Pass Models scored 2 models we track, plus 8 other entries on its leaderboard.
  • Warning Newest score The newest came 10 months ago, in January 2026, for Qwen3-VL-Embedding-2B.
  • Note Frontier models None of its models are on the capabilities index.
  • Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
  • Pass Importer We read the board on arxiv.org: 2 rows for models we track and 8 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