MultiClinSum
Version 1
Models summarize clinical case reports in English, Spanish, French, and Portuguese. Organizers compare each summary with a reference using ROUGE and BERTScore.
Ten teams submitted 50 runs. MaLei used GPT-4 and GPT-4o. The public English test contains 3,396 cases with reference summaries.
- Made by
- Barcelona Supercomputing Center
- Released
- April 2025
- Kind
- Medicine
- Level
- University
- Scored
- Checked automatically
- Answers
- Open-ended
- Tasks
- All public
- Measures
- Capability
- Subject
- Clinical medicine
- Language
- English, Spanish, French, Portuguese
- Interaction
- Single turn
- Items from
- Real work and use
- Refresh
- New versions replace it
- Run by
- Anyone
- In views
- Biology and medicine
- Last model added
- September 2024
- Scores refreshed
- November 20th, 2026
LLaMA3.1-Instruct tops the leaderboard with 0.87 Qwen2.5-0.5B leads with 0.86
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 this is the English BERTScore F1 column. 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 Qwen2.5-0.5B, at 0.86. This view shows only models we track, each at its best.
- 1 LLaMA3.1-Instruct 0.87
- 2 Qwen3 0.86
- 3 Qwen2.5 / Phi-4 0.86
- 4
Qwen2.5-0.5B 0.86
- 5 GPT4 (snapshot unspecified) 0.85
- 6 BERT 0.84
Source: The MultiClinSum paper
- 1
Qwen2.5-0.5B 0.86
Source: The MultiClinSum paper
| # | Entry | Score | Setting | Submitted by | Date | Source |
|---|---|---|---|---|---|---|
| 1 | LLaMA3.1-Instruct | 0.87 | seemdog | Official leaderboard | ||
| 2 | Qwen3 | 0.86 | pjmathematician | Official leaderboard | ||
| 3 | Qwen2.5 / Phi-4 | 0.86 | MedCOD | Official leaderboard | ||
| 4 | | 0.86 | BU team | Sep 2024 | Official leaderboard | |
| 5 | GPT4 (snapshot unspecified) | 0.85 | MaLei | Official leaderboard | ||
| 6 | BERT | 0.84 | ExtraSum | Official leaderboard |
| # | Model | Score | Setting | Submitted by | Date | Source |
|---|---|---|---|---|---|---|
| 1 | | 0.86 | BU team | Sep 2024 | Official leaderboard |
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: Official MultiClinSum 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.
Versions
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 8 checks pass. Every benchmark
Catalog record 2 pass
- Pass Task access All tasks are public.
- Pass Confidence Checked against a primary source.
Scores 2 pass 3 notes
- Pass Independent runs Scores from the benchmark’s paper (6 entries).
- Pass Models scored 1 model we track, plus 5 other entries on its leaderboard.
- Note Newest score The newest came 2 years ago, in September 2024, for Qwen2.5-0.5B. That’s expected for a test replaced by MultiClinSum-2.
- 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 ceur-ws.org: 1 row for models we track and 5 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.