HealthCare.gov
Welcome to the Health Insurance Marketplace®. Official government website.
- healthcare.gov
- MarketUS
- Localesen, es-US
- Rank
- Top 35%
- #191
- Government rank
- Sector average 77.8
- #4
- Benchmark runs
- 3 providersAcross 3 providers
- 5
- Government avg
- 77.8 (+3.7)
- Market avg
- 76.7 (+4.8)
01
Latest results
HealthCare.gov ranks #191 of 550 scored sites, up 45 places since the last run.
- This site
- Government
- Market
By category
- Brand awareness93up 2.1
- Discovery88up 6.0
- Information retrieval90down 2.5
- Market ranking50up 6.9
- Accuracy850.0
- Task completion82down 8.0
- Delegated access62down 37.7
- Contact & communication730.0
Table view
Monthly medians. Dates in UTC.
02
Performance
Site checks, then AI agents on real tasks.
Automated checks probe the site before any agent runs. With no sessions yet, they count in full. Strongest is Brand awareness at 84.0, weakest is Market ranking at 21.0.
Site checks by category
- Brand awareness
- 84.0
- Discovery
- 76.0
- Information retrieval
- 80.0
- Market ranking
- 21.0
- Accuracy
- 70.0
- Task completion
- 65.0
- Delegated access
- 35.0
- Contact & communication
- 50.0
01 Site checks
Points by category
- Brand awareness84.0
- Discovery76.0
- Information retrieval80.0
- Market ranking21.0
- Accuracy70.0
- Task completion65.0
- Delegated access35.0
- Contact & communication50.0
02 Agent sessions
Brand awareness
Brand awareness
QueuedBrand awareness
QueuedBrand awareness
Queued
Discovery
Discovery
QueuedDiscovery
QueuedDiscovery
Queued
Information retrieval
Information retrieval
QueuedInformation retrieval
QueuedInformation retrieval
Queued
Market ranking
Market ranking
QueuedMarket ranking
QueuedMarket ranking
Queued
Accuracy
Accuracy
QueuedAccuracy
QueuedAccuracy
Queued
Task completion
Task completion
QueuedTask completion
QueuedTask completion
Queued
Delegated access
Find whether someone can act on another person's behalf (a representative, nominee, agent or power of attorney) and whether the agency…
Found the representative or nominee process (40pts). Correctly identified the access model (40pts). Found published APIs or open data, or correctly reported there are none (20pts). Deduct 20pts if none exists but that is the correct answer.
QueuedFind whether someone can act on another person's behalf (a representative, nominee, agent or power of attorney) and whether the agency…
Found the representative or nominee process (40pts). Correctly identified the access model (40pts). Found published APIs or open data, or correctly reported there are none (20pts). Deduct 20pts if none exists but that is the correct answer.
QueuedFind whether someone can act on another person's behalf (a representative, nominee, agent or power of attorney) and whether the agency…
Found the representative or nominee process (40pts). Correctly identified the access model (40pts). Found published APIs or open data, or correctly reported there are none (20pts). Deduct 20pts if none exists but that is the correct answer.
Queued
Contact & communication
Find how to contact the agency (phone, online enquiry, office locations) and how to lodge a complaint or request a review of a decision.
Found a working contact channel (50pts). Found the complaint or review process (50pts). Deduct 20pts for each dead end or missing detail.
QueuedFind how to contact the agency (phone, online enquiry, office locations) and how to lodge a complaint or request a review of a decision.
Found a working contact channel (50pts). Found the complaint or review process (50pts). Deduct 20pts for each dead end or missing detail.
QueuedFind how to contact the agency (phone, online enquiry, office locations) and how to lodge a complaint or request a review of a decision.
Found a working contact channel (50pts). Found the complaint or review process (50pts). Deduct 20pts for each dead end or missing detail.
Queued
03 Blend
- Agents 60%
- Checks 40%
One kind of evidence only? That kind counts in full.
- Brand awareness10% of the overallSite checks only: 84.0 raw84.0 raw → 92.5 published
- Discovery15% of the overallSite checks only: 76.0 raw76.0 raw → 88.4 published
- Information retrieval15% of the overallSite checks only: 80.0 raw80.0 raw → 90.4 published
- Market ranking10% of the overallSite checks only: 21.0 raw21.0 raw → 49.5 published
- Accuracy15% of the overallSite checks only: 70.0 raw70.0 raw → 85.2 published
- Task completion20% of the overallSite checks only: 65.0 raw65.0 raw → 82.4 published
- Delegated access10% of the overallSite checks only: 35.0 raw35.0 raw → 62.3 published
- Contact & communication5% of the overallSite checks only: 50.0 raw50.0 raw → 73.2 published
04 Benchmarked score
63.4 raw → 81.5
Category weights
- Brand awareness 10%
- Discovery 15%
- Information retrieval 15%
- Market ranking 10%
- Accuracy 15%
- Task completion 20%
- Delegated access 10%
- Contact & communication 5%
Overall 81.5, from 63.4 raw points.
Agents
Latest run in progress: 24 of 24 sessions to finish.
Claude
- Latest run average
- Run in progress
- Government median
- 100.0
Sessions
Brand awareness
QueuedDiscovery
QueuedInformation retrieval
QueuedMarket ranking
QueuedAccuracy
QueuedTask completion
QueuedDelegated access
Find whether someone can act on another person's behalf (a representative, nominee, agent or power of attorney) and whether the agency…
Found the representative or nominee process (40pts). Correctly identified the access model (40pts). Found published APIs or open data, or correctly reported there are none (20pts). Deduct 20pts if none exists but that is the correct answer.
QueuedContact & communication
Find how to contact the agency (phone, online enquiry, office locations) and how to lodge a complaint or request a review of a decision.
Found a working contact channel (50pts). Found the complaint or review process (50pts). Deduct 20pts for each dead end or missing detail.
Queued
ChatGPT Agent
- Latest run average
- Run in progress
- Government median
- 100.0
Sessions
Brand awareness
QueuedDiscovery
QueuedInformation retrieval
QueuedMarket ranking
QueuedAccuracy
QueuedTask completion
QueuedDelegated access
Find whether someone can act on another person's behalf (a representative, nominee, agent or power of attorney) and whether the agency…
Found the representative or nominee process (40pts). Correctly identified the access model (40pts). Found published APIs or open data, or correctly reported there are none (20pts). Deduct 20pts if none exists but that is the correct answer.
QueuedContact & communication
Find how to contact the agency (phone, online enquiry, office locations) and how to lodge a complaint or request a review of a decision.
Found a working contact channel (50pts). Found the complaint or review process (50pts). Deduct 20pts for each dead end or missing detail.
Queued
Gemini
- Latest run average
- Run in progress
- Government median
- 100.0
Sessions
Brand awareness
QueuedDiscovery
QueuedInformation retrieval
QueuedMarket ranking
QueuedAccuracy
QueuedTask completion
QueuedDelegated access
Find whether someone can act on another person's behalf (a representative, nominee, agent or power of attorney) and whether the agency…
Found the representative or nominee process (40pts). Correctly identified the access model (40pts). Found published APIs or open data, or correctly reported there are none (20pts). Deduct 20pts if none exists but that is the correct answer.
QueuedContact & communication
Find how to contact the agency (phone, online enquiry, office locations) and how to lodge a complaint or request a review of a decision.
Found a working contact channel (50pts). Found the complaint or review process (50pts). Deduct 20pts for each dead end or missing detail.
Queued
03
Potential improvements
Fix where agents got stuck, then lift your biggest categories.
No discoverable MCP server. Agents and AI clients have no way to discover one automatically.
Biggest wins
Lifting Delegated access to Good adds about +0.7 on its own, taking the overall from 81.5 to 82.2.
Raise Delegated access from 62.3 to 72 (Good) to add about 0.7 to the overall score.
Raise Market ranking from 49.5 to 58 (OK) to add about 0.5 to the overall score.
Raise Contact & communication from 73.2 to 85 (Excellent) to add about 0.5 to the overall score.
Each gain assumes only that category improves. Fix several and the total lands a little under their sum.
Where agents get stuck
10 improvements from the latest run, 1 of them high severity.
- High
- 1
- Medium
- 7
- Low
- 2
- HighDelegated access
No discoverable MCP server. Agents and AI clients have no way to discover one automatically.
- MediumBrand awareness
No Organization JSON-LD. Agents can’t tell who owns the site at a glance.
- MediumInformation retrieval
No JSON-LD structured data. Agents must infer entities from markup.
Where agents get stuck
No discoverable MCP server. Agents and AI clients have no way to discover one automatically.
No Organization JSON-LD. Agents can’t tell who owns the site at a glance.
No JSON-LD structured data. Agents must infer entities from markup.
No Product/Service schema on the homepage. Agents can’t easily compare offerings.
No JSON-LD at all. Every factual claim must be inferred from prose.
No mention of delegated auth primitives (passkey, OAuth, MCP). Agents must drive a full browser session.
No OAuth/OIDC discovery metadata. Agents cannot bootstrap a scoped, revocable session; any delegation falls back to password sharing.
No contact email visible in server-rendered HTML. Agents can’t fall back to email.
No review or aggregateRating schema. Agents have no signal for ranking vs peers.
No detectable agentic-commerce rail (Stripe SPT, Shopify/UCP, PayPal ACP). Agent-initiated payment needs custom work.
Want to find these in your own flows before an agent does? Read how to test your product for AI agent users.
Technical readiness
Robots, sitemaps, llms.txt, structured data and more, checked by Is Agentic.
Protocol baseline by Is Agentic
No Is Agentic report for healthcare.gov yet
Badge
Show visitors your Good agent score
Add a live Index badge to your footer, docs or README. The badge updates after every run and links visitors to this scorecard.
Ask your agent about healthcare.gov
Add the Index to Claude, ChatGPT or Cursor as an MCP connector to look up any score, frictions and agent sessions. No account needed.
https://app.stuntdouble.io/api/mcp/indexDiscover more insights with Stunt Double
Send AI agents through healthcare.gov on your own tasks.