actAVA Benchmarks· CHI-Bench v1.0.0

The world’s first long-horizon healthcare benchmark for AI agents.

Built with the clinicians who do the work.

actAVA partners with 20+ hospitals and top universities to evaluate frontier agents across prior authorization, utilization management, and care management. The best agent today resolves 28% of tasks at pass@1; end-to-end prior authorization automation drops to 0%.

01CHI-Bench Overview· 2:39

Benchmarking agentic AI for healthcare administration.

See how CHI-Bench evaluates whether AI agents can reliably navigate real healthcare administrative workflows — across policies, applications, roles, evidence, and long sequences of actions.

0220+ Clinical & Academic Collaborators
Johns Hopkins MedicineWellstar Health SystemYale School of MedicineStanford UniversityCMUUniversity of OxfordUSCUCSDBrown UniversityEmory UniversityUniversity of WashingtonNortheasternArizona StateUICBoston CollegeStony BrookMBZUAI+3 more
Domains
0
PA · UM · CM
Tasks
0
25 per domain
Agent configs
0
harness × model
Best pass@1
0.0%
Claude Code · Opus 4.6
MCP tools
0+
21 healthcare apps
Handbook docs
0
policy corpus
03See It in Motion

One agent, one trial, one final scorecard.

Each animation replays an actual trajectory from the claude-code-opus-4-6 submission — stage transitions, real tool calls, real policy gates, real scorecard outcomes.

Task pa_t00869 steps · 7m41s
Reward0.00 · 7/11
Seat 1 · provider intake
Clinical Intake Clerk
chart.search_patients
chart.get_patient_chart
chart.list_candidate_orders
people.list_ordering_providers
Seat 2 · case construction
PA Coordinator
cases.create_from_ordercode=43775 · site=outpatient
forms.list_required_forms
Seat 3 · documentation review
Clinical Reviewer
docs.upload_evidencechart_note
docs.upload_evidencelab_result
forms.save_form_responsequestionnaire
docs.upload_evidenceletter_of_medical_necessity
Seat 4 · disposition + submit
PA Submitter
docs.create_submission_bundle
auth.finalize_provider_determinationfinal_action=submit_pa
auth.submit_authorization
auth.check_status
Medical Policy · 2026T0362QQ
Bariatric Surgery
BMI ≥ 40 documented
42.3
Two supervised programs documented
Procedure code 43775 on covered list
Site of service must be inpatient_hospital
agent submitted outpatient
Pre-op psych eval completed (referral ≠ done)
!
final_action should be gather_more_evidence
00:00
00:32↻ auto-loops

An RN drives a clinical referral from chart pull through policy lookup, evidence assembly, and a final action decision. Every stage commits — there is no retry.

Best pass@1
29.3%
Codex + GPT-5.5

Why it’s hard · One wrong site-of-service flip cascades into four scorecard failures.

04Why CHI-Bench Is Hard

Three capabilities underrepresented in current benchmarks.

Axes

Long-horizon

60–80 agent steps per trial across 4–6 distinct stages, with state that carries forward and can't be retried after commit.

Role-composed

One agent plays many seats — intake clerk, nurse, medical director, peer-to-peer reviewer, letter center — and each seat writes its own artifact.

Policy-driven

Medical-policy criteria, site-of-service rules, consent scripts, evidence-grounding requirements — checked by deterministic rubrics plus an LLM semantic judge.

05Get Involved

Run a submission. Or read the methodology.

The benchmark code, dataset, and 1,279-page operations handbook are open. The leaderboard is live.

Leaderboard

30 agent configurations — harness × model — ranked across prior authorization, utilization management, and care management.

View the leaderboard

75 tasks

25 per domain, each one a full working trial: seats, tools, policy gates, and a final scorecard.

Browse the tasks

Docs

The methodology, the environment, and the submission guide — grounded in a 1,279-document operations corpus.

Read the docs
The agentic future · For healthcare

Master your agentic future.

Don't give your agentic future away to a single model provider. Don't mistake consumer tools in the business for real, safe Enterprise Agentic Tools. Enable your citizen developers to create and manage the AI Agents they need to run their part of your business. actAVA is the AI factory for healthcare.

Connect with us today to discover how actAVA KORA, CHRYSO, and our team of experts can supercharge your pathway to workforce transformation through agentic AI.