RadSum23
Models write the impression section of radiology reports from findings. One track includes chest images. Organizers rank submissions by RadGraph F1.
The shs-nlp team adapted BLOOMZ for the challenge. MIMIC data require signed PhysioNet agreements. The hidden chest test includes Stanford cases.
- Made by
- Stanford University
- Released
- January 2023
- Kind
- Medicine
- Level
- Expert
- Scored
- Checked automatically
- Answers
- Open-ended
- Tasks
- Kept private
- Measures
- Capability
- Subject
- Clinical medicine
- Language
- English
- Interaction
- Single turn
- Items from
- Real work and use, Another benchmark
- Refresh
- One fixed set
- Run by
- A host
- In views
- Vision, Biology and medicine
- Scores refreshed
- November 20th, 2026
RadBloomz tops the leaderboard with 39.8 T5-Base leads with 38.0
Best score per entry from the benchmark's paper, read on November 20th, 2026. A paper’s table doesn’t add newer models. The papers report no overall score, so the headline is the plain mean of F1-RadGraph across the four test sets. 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 T5-Base, at 38.0. This view shows only models we track, each at its best.
- 1 RadBloomz Zero-shot 39.8
- 2 BART Fine-tuned on MIMIC-III with further fine-tuning for MIMIC-CXR 38.0
- 3 T5-Base Fine-tuned on MIMIC-III with further fine-tuning for MIMIC-CXR 38.0
Source: The RadSum23 paper
Source: The RadSum23 paper
| # | Entry | Score | Setting | Submitted by | Date | Source |
|---|---|---|---|---|---|---|
| 1 | RadBloomz | 39.8 | Zero-shot | shs-nlp | Official leaderboard | |
| 2 | BART | 38.0 | Fine-tuned on MIMIC-III with further fine-tuning for MIMIC-CXR | KnowLab | Official leaderboard | |
| 3 | T5-Base | 38.0 | Fine-tuned on MIMIC-III with further fine-tuning for MIMIC-CXR | KnowLab | Official leaderboard |
| # | Model | Score | Setting | Submitted by | Date | Source |
|---|---|---|---|---|---|---|
| 1 | T5-Base | 38.0 | Fine-tuned on MIMIC-III with further fine-tuning for MIMIC-CXR | KnowLab | Official leaderboard |
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
No dated values yet.
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
All 7 checks pass. Every benchmark
Catalog record 2 pass
- Pass Task access The tasks are private.
- Pass Confidence Checked against a primary source.
Scores 1 pass 4 notes
- Pass Independent runs Scores from the benchmark’s paper (3 entries).
- Note Models scored Only 1 model we track, plus 2 other entries on its leaderboard.
- Note Newest score No scores yet.
- 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 aclanthology.org: 1 row for models we track and 2 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.