Benchmark Almanac

HealthAgentBench V2

Claude Opus 5.5 57.3% leads since October 2026
Not in model cards
Version 2

Agents complete 75 healthcare tasks across nine categories in terminal environments. Task-specific verifiers check outputs against hidden labels, with model grading for radiology report correction.

Version 2 removes two categories, adds four, and disables web access. The maker reports unresolved contextual review of some survival-prediction trajectories.

Released
October 2026
Kind
Medicine
Level
Expert
Scored
Checked automatically
Answers
Agent task
Tasks
Public, plus a private test set
Measures
Capability
Language
English
In and out
Text, Images, 3D, Tables → Text, Actions, Code
Interaction
Agentic
Environment
Terminal
Items from
Another benchmark
Run by
Anyone
Based on
HealthAgentBench
Strongest model tested
GPT-6 Astra #4 on the capability index
Last model added
September 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.

Abstract of HealthAgentBench: A Unified Benchmark Suite of Realistic Agentic Healthcare Environments for Challenging Frontier AI Agents (arXiv:2606.31179, CC0)
6
Models scored on its own leaderboard

Claude Opus 5.5 leads with 57.3% among models released by September 2026

Best score per model from the benchmark's own leaderboard, read on November 19th, 2026. Where a model ran with several settings or harnesses, we keep its best.

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:

  1. 1 Claude Opus 5.5 57.3%
  2. 2 GPT-6 Astra 50.7%
  3. 3 Claude Sonnet 5.5 50.7%
  4. 4 GPT-6 Sol 41.3%
  5. 5 GPT-5.6 Sol 34.7%
  6. 6 Claude Opus 5 32%

Source: Official HealthAgentBench V2 leaderboard

#ModelScoreSettingDateSource
1 Claude Opus 5.5 57.3% Claude Code Sep 2026 Official leaderboard
2 GPT-6 Astra 50.7% Codex Sep 2026 Official leaderboard
3 Claude Sonnet 5.5 50.7% Claude Code Sep 2026 Official leaderboard
4 GPT-6 Sol 41.3% Codex Sep 2026 Official leaderboard
5 GPT-5.6 Sol 34.7% Codex Jul 2026 Official leaderboard
6 Claude Opus 5 32% Claude Code Jul 2026 Official leaderboard

Number one over time

Lab claims count from the day the card came out, independent runs from the model’s release.

Anthropic
Own leaderboard Not tested since Oct 2026

Source: Official HealthAgentBench V2 leaderboard

Scores over time

All the scores we have, one dot each, so a model tested at several settings appears more than once.

Plot with other benchmarks
On the benchmark’s own leaderboard Best so far
0% 20% 40% 60% 80% 100% Near the ceiling (85%) Claude Opus 5.5 GPT-6 Astra GPT-5.6 Sol 0% 20% 40% 60% 80% 100% Near the ceiling (85%) Claude Opus 5.5 GPT-6 Astra

Source: Official HealthAgentBench V2 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.

OpenAI Anthropic
HealthAgentBench V2 Not tested since Oct 2026
HealthAgentBench Replaced by V2, Oct 2026
HealthAgentBench V2 Not tested since Oct 2026

Source: Official leaderboards

More in Law, finance and medicine

All 637 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 11 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 5 pass
  • Pass Independent runs Scores from the official leaderboard (6 entries).
  • Pass Models scored 6 models we track.
  • Pass Newest score The newest is from September 2026, for Claude Sonnet 5.5.
  • Pass Frontier models 3 of the top 10 have a score, led by GPT-6 Astra (#4).
  • Pass Headroom The best is 57.3%, under 85%, so it still separates models.
Leaderboard import 3 pass
  • Pass Importer We read the board on microsoft.github.io: 6 rows for models we track 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.

How we check