Hx2Dx ARENA
Models interview a simulated patient, request examinations and tests, and give a diagnosis. A judge compares the diagnosis with the published case.
- Made by
- Federico Ravenda and colleagues
- Released
- November 2026
- Kind
- Medicine
- Level
- Expert
- Scored
- Graded by a model
- Answers
- Agent task
- Measures
- Capability
- Subject
- Clinical medicine
- Language
- English
- Interaction
- Agentic
- Environment
- A simulator
- Items from
- Real work and use, Generated
- Refresh
- One fixed set
- Run by
- A host
- Occupations
- Healthcare practitioners and technical
- In views
- Agents, Vision, Robotics, Biology and medicine
- Strongest model tested
-
DeepSeek V4.1 Flash #34 on the capability index
- Last model added
- September 2026
- Scores refreshed
- November 20th, 2026
GPT-6 Luna leads with 83.9% among models released by September 2026
Best score per model 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. Every run is in the next chart.
The newest model with a score here came out in September 2026, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:
- GPT-6.2 Astra
- Claude Fable 5.2
-
Gemini 4 Carbon
- GPT-6.1 Sol
- and 16 more
- 1 GPT-6 Luna Static 83.9%
- 2 GLM-5.3-Flash Static 79.7%
- 3
DeepSeek V4.1 Flash Static 75.1%
- 4
Gemini 3.5 Flash-Lite Static 74.7%
- 5
Llama 4 Scout Static 57.9%
- 6
Ministral 8B Static 56.1%
- 7
Gemma 3 27B Static 55.1%
Source: The Hx2Dx ARENA paper
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | GPT-6 Luna | 83.9% | Static | Sep 2026 | Official leaderboard |
| 2 | GLM-5.3-Flash | 79.7% | Static | Aug 2026 | Official leaderboard |
| 3 | | 75.1% | Static | Sep 2026 | Official leaderboard |
| 4 | | 74.7% | Static | Jul 2026 | Official leaderboard |
| 5 | | 57.9% | Static | Apr 2025 | Official leaderboard |
| 6 | | 56.1% | Static | Oct 2024 | Official leaderboard |
| 7 | | 55.1% | Static | Mar 2025 | Official leaderboard |
Scores at each effort level
Models the leaderboard ran at two or more effort levels. We don’t have enough cost data here to say what the extra effort costs.
Source: The Hx2Dx ARENA paper
| Model | Effort | Harness | Score | Cost per task | Output tokens |
|---|---|---|---|---|---|
| GPT-6 Luna | Static | 83.9% | |||
| GLM-5.3-Flash | Static | 79.7% | |||
| Static | 75.1% | ||||
| Static | 74.7% | ||||
| Static | 57.9% | ||||
| Static | 56.1% | ||||
| Static | 55.1% | ||||
| GLM-5.3-Flash | Conversational | 54.4% | |||
| Conversational | 50.3% | ||||
| GPT-6 Luna | Conversational | 47.4% | |||
| Conversational | 38.5% | ||||
| Conversational | 25.7% | ||||
| Conversational | 23.6% | ||||
| Conversational | 21.9% |
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: The Hx2Dx ARENA paper
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: Official Hx2Dx ARENA 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
- 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 Task access check. We don’t know whether the tasks are public. Every benchmark
Catalog record 1 warning 1 pass
- Warning Task access We don’t know whether the tasks are public.
- Pass Confidence Checked against a primary source.
Scores 4 pass 1 note
- Pass Independent runs Scores from the benchmark’s paper (7 entries).
- Pass Models scored 7 models we track.
- Pass Newest score The newest is from September 2026, for GPT-6 Luna.
- Note Frontier models None of the top 10 has a score. The strongest tested is DeepSeek V4.1 Flash (#34).
- Pass Headroom The best is 83.9%, under 85%, so it still separates models.
Leaderboard import 3 pass
- Pass Importer We read the board on arxiv.org: 14 rows for models we track 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.