HealthAgentBench
Version 1
Agents use terminal tools to complete 54 clinical and biomedical tasks across seven categories. Task-specific verifiers measure success, including a model judge for radiology report correction.
The original leaderboard pools three attempts per task. Some source datasets require separate access approval.
- Made by
- Microsoft Research
- Released
- June 2026
- Kind
- Medicine
- Level
- Expert
- Scored
- Checked automatically
- Answers
- Agent task
- Tasks
- Public, plus a private test set
- Measures
- Capability
- Subject
- Clinical medicine, Medical biotechnology
- Language
- English
- Interaction
- Agentic
- Environment
- Terminal
- Refresh
- New versions replace it
- Run by
- A host
- In views
- Agents, Vision, Biology and medicine
- Strongest model tested
- Claude Opus 5 #11 on the capability index
- Last model added
- July 2026
- Scores refreshed
- November 19th, 2026
In the authors’ words
As AI agents become increasingly capable of complex, long-horizon reasoning, rigorous evaluation is essential for measuring progress toward real-world healthcare applications. However, existing healthcare benchmarks are often static or narrow in clinical scope, motivating broader evaluation of agents acting on raw patient data. We introduce HealthAgentBench, a suite of 75 agentic healthcare tasks across 9 categories each with its unique environment. The benchmark suite spans diagnosis, specimen assessment, research, and data management workflows and a broad range of modalities. Each task is designed to replicate an end-to-end clinical workflow: given task instructions and supporting resources, an agent must explore raw healthcare data, operate within a complex environment, and execute multi-step solutions that go beyond naive prompting, such as querying large clinical databases or interpreting gigapixel pathology images. All tasks are scored using binary success criteria derived from reference labels, executable rules, or computational baselines. We evaluate six agents (three GPT models through Codex and three Claude models through Claude Code) with one scored attempt per task (450 evaluations). Overall success ranges from 32.0% to 57.3%; Claude Code Opus-5.5 leads with a 57.3% success rate, followed by GPT-6-astra and Sonnet-5.5 at 50.7% each. Performance varies substantially by category with specialized imaging modalities such as CT and MRI being especially difficult. HealthAgentBench provides a challenging and realistic benchmark with substantial room for future progress. We release our benchmark athttps://github.com/microsoft/HealthAgentBench.
Claude Opus 5 leads with 55% among models released by July 2026 Claude Opus 5 leads with 55% among models released by July 2026
Best score per entry from the benchmark's own leaderboard, read on November 19th, 2026. Where a model ran with several settings or harnesses, we keep its best. Every run is in the next chart. 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.
The newest model with a score here came out in July 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 Astra
- and 14 more
- 1 Claude Opus 5 55%
- 2 GPT-5.6 Sol 45%
- 3 GPT-5.5 42%
- 4 Claude Opus 4.8 36%
- 5 GPT-5.4 28%
- 6 Claude Opus 4.7 27%
- 7 GPT 5.3 22%
- 8 Claude Opus 4.6 19%
- 9 Claude Sonnet 4.6 17%
- 10 GPT-5.4 Mini 16%
Source: Official HealthAgentBench leaderboard
- 1 Claude Opus 5 55%
- 2 GPT-5.6 Sol 45%
- 3 GPT-5.5 42%
- 4 Claude Opus 4.8 36%
- 5 GPT-5.4 28%
- 6 Claude Opus 4.7 27%
- 7 Claude Opus 4.6 19%
- 8 Claude Sonnet 4.6 17%
- 9 GPT-5.4 Mini 16%
Source: Official HealthAgentBench leaderboard
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Claude Opus 5 | 55% | Claude Code | Jul 2026 | Official leaderboard |
| 2 | GPT-5.6 Sol | 45% | Codex | Jul 2026 | Official leaderboard |
| 3 | GPT-5.5 | 42% | Codex | Apr 2026 | Official leaderboard |
| 4 | Claude Opus 4.8 | 36% | Copilot | May 2026 | Official leaderboard |
| 5 | GPT-5.4 | 28% | Codex | Mar 2026 | Official leaderboard |
| 6 | Claude Opus 4.7 | 27% | Claude Code | Apr 2026 | Official leaderboard |
| 7 | GPT 5.3 | 22% | Codex | Official leaderboard | |
| 8 | Claude Opus 4.6 | 19% | Claude Code | Feb 2026 | Official leaderboard |
| 9 | Claude Sonnet 4.6 | 17% | Claude Code | Feb 2026 | Official leaderboard |
| 10 | GPT-5.4 Mini | 16% | Codex | Mar 2026 | Official leaderboard |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Claude Opus 5 | 55% | Claude Code | Jul 2026 | Official leaderboard |
| 2 | GPT-5.6 Sol | 45% | Codex | Jul 2026 | Official leaderboard |
| 3 | GPT-5.5 | 42% | Codex | Apr 2026 | Official leaderboard |
| 4 | Claude Opus 4.8 | 36% | Copilot | May 2026 | Official leaderboard |
| 5 | GPT-5.4 | 28% | Codex | Mar 2026 | Official leaderboard |
| 6 | Claude Opus 4.7 | 27% | Claude Code | Apr 2026 | Official leaderboard |
| 7 | Claude Opus 4.6 | 19% | Claude Code | Feb 2026 | Official leaderboard |
| 8 | Claude Sonnet 4.6 | 17% | Claude Code | Feb 2026 | Official leaderboard |
| 9 | GPT-5.4 Mini | 16% | Codex | Mar 2026 | Official leaderboard |
The best score, 55%, costs $3.30 a task
Runs on the cost frontier score higher than any run that's cheaper. The costs are the leaderboard's own estimates, so compare them only within this benchmark.
Source: Official HealthAgentBench leaderboard
| Model | Effort | Harness | Score | Cost per task | Output tokens |
|---|---|---|---|---|---|
| Claude Opus 5 | Claude Code | 55% | $3.30 | ||
| GPT-5.6 Sol | Codex | 45% | $5.20 | ||
| GPT-5.5 | Codex | 42% | $2.80 | ||
| Claude Opus 4.8 | Copilot | 36% | $3.10 | ||
| GPT-5.5 | Copilot | 35% | $2.60 | ||
| Claude Opus 4.8 | Claude Code | 32% | $4.00 | ||
| GPT-5.4 | Codex | 28% | $1.30 | ||
| Claude Opus 4.7 | Claude Code | 27% | $4.80 | ||
| Claude Opus 4.6 | Claude Code | 19% | $4.10 | ||
| Claude Sonnet 4.6 | Claude Code | 17% | $2.90 | ||
| GPT-5.4 Mini | Codex | 16% | $0.60 |
The best score, 55%, costs $3.30 a task
Runs on the cost frontier score higher than any run that's cheaper. The costs are the leaderboard's own estimates, so compare them only within this benchmark.
Source: Official HealthAgentBench leaderboard
| Model | Effort | Harness | Score | Cost per task | Output tokens |
|---|---|---|---|---|---|
| Claude Opus 5 | Claude Code | 55% | $3.30 | ||
| GPT-5.6 Sol | Codex | 45% | $5.20 | ||
| GPT-5.5 | Codex | 42% | $2.80 | ||
| Claude Opus 4.8 | Copilot | 36% | $3.10 | ||
| GPT-5.5 | Copilot | 35% | $2.60 | ||
| Claude Opus 4.8 | Claude Code | 32% | $4.00 | ||
| GPT-5.4 | Codex | 28% | $1.30 | ||
| Claude Opus 4.7 | Claude Code | 27% | $4.80 | ||
| Claude Opus 4.6 | Claude Code | 19% | $4.10 | ||
| Claude Sonnet 4.6 | Claude Code | 17% | $2.90 | ||
| GPT-5.4 Mini | Codex | 16% | $0.60 |
3 models have held number one on the official leaderboard since its release in June 2026
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: Official HealthAgentBench 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 HealthAgentBench 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
We switch the top row to each new version when it comes out. Open it for one row per version. An old version stays in play while people still test it, so whoever first takes it past 85% gets credit for closing it out.
Source: Official leaderboards
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 10 checks pass. Every benchmark
Catalog record 2 pass
- Pass Task access Public tasks, plus a private test set.
- Pass Confidence Checked against a primary source.
Scores 4 pass 1 note
- Pass Independent runs Scores from the official leaderboard (10 entries).
- Pass Models scored 9 models we track, plus 1 other entry on its leaderboard.
- Pass Newest score The newest is from July 2026, for Claude Opus 5.
- Note Frontier models None of the top 10 has a score, which is fine for a retired test. The strongest tested is Claude Opus 5 (#11).
- Pass Headroom The best is 55%, under 85%, so it still separates models.
Leaderboard import 3 pass
- Pass Importer We read the board on microsoft.github.io: 11 rows for models we track and 1 other entry at the last read.
- Pass Last read November 19th, 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.