PWS-Health
Version health
Web research systems answer healthcare questions from clinical trials, medical literature, registries, drug labels, and healthcare workflows.
The benchmark has 133 held-out questions with verified answers. Parallel reports results for six search systems, with 85.2% for Parallel Fast and 66.9% for Claude native search.
- Made by
- Parallel Web Systems
- Released
- November 2026
- Kind
- Medicine
- Level
- Expert
- Scored
- Graded by a model
- Answers
- Agent task
- Tasks
- Kept private
- Measures
- Capability
- Subject
- Health sciences
- Language
- English
- Interaction
- Agentic
- Environment
- Browser, APIs and tools
- Items from
- Real work and use
- Refresh
- One fixed set
- Run by
- A host
- In views
- Agents, Biology and medicine
Parallel Fast tops the leaderboard with 85.2%
Best score per entry from the benchmark's own leaderboard, read on November 21st, 2026. 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.
- 1 Parallel Fast Claude Opus 5.5 high effort answer model 85.2%
- 2 Parallel Advanced Claude Opus 5.5 high effort answer model 83.7%
- 3 Exa Claude Opus 5.5 high effort answer model 82.5%
- 4 Perplexity Claude Opus 5.5 high effort answer model 80.5%
- 5 Tavily Claude Opus 5.5 high effort answer model 77.2%
- 6 Claude native search Claude Opus 5.5 high effort answer model 66.9%
Source: Official PWS-Health leaderboard
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Parallel Fast | 85.2% | Claude Opus 5.5 high effort answer model | Official leaderboard | |
| 2 | Parallel Advanced | 83.7% | Claude Opus 5.5 high effort answer model | Official leaderboard | |
| 3 | Exa | 82.5% | Claude Opus 5.5 high effort answer model | Official leaderboard | |
| 4 | Perplexity | 80.5% | Claude Opus 5.5 high effort answer model | Official leaderboard | |
| 5 | Tavily | 77.2% | Claude Opus 5.5 high effort answer model | Official leaderboard | |
| 6 | Claude native search | 66.9% | Claude Opus 5.5 high effort answer model | Official leaderboard |
Accuracy versus cost
The line joins the runs that no other run beats on both measures. We redrew this chart from the numbers on the official leaderboard.
| Model | Setting | Accuracy | Cost per 1,000 questions |
|---|---|---|---|
| Parallel Fast | Claude Opus 5.5 high effort answer model | 85.2% | $104 |
| Parallel Advanced | Claude Opus 5.5 high effort answer model | 83.7% | $85.3 |
| Exa | Claude Opus 5.5 high effort answer model | 82.5% | $124.6 |
| Perplexity | Claude Opus 5.5 high effort answer model | 80.5% | $116.2 |
| Tavily | Claude Opus 5.5 high effort answer model | 77.2% | $154.3 |
| Claude native search | Claude Opus 5.5 high effort answer model | 66.9% | $646 |
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 The tasks are private.
- Pass Confidence Checked against a primary source.
Scores 2 pass 3 notes
- Pass Independent runs Scores from the official leaderboard (6 entries).
- Pass Models scored 6 entries on its leaderboard, none a model we track.
- Note Newest score No scores yet.
- Note Frontier models No models scored yet.
- Note Headroom No scores yet.
Leaderboard import 3 pass
- Pass Importer We read the board on parallel.ai: 6 entries at the last read, none a model we track.
- Pass Last read November 21st, 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.