HomieBench v3: the best AI for realtors, ranked by finished work.
HomieBench compares the models behind today’s best realtor AI assistants across offers, CRM, lead generation, marketing, CMAs, showings, MLS research, document review, and closings. Kimi K3 takes the projected v3 lead—but it does not win every kind of realtor work.
Kimi K3 is newly available. Its v3 placement is a scenario projection from official model and pricing evidence plus HomieBench priors—not a claim that the repeatable identical-harness run is already complete.
- frontier models
- 8
- realtor workflows
- 100
- job families
- 8
- shared harness
- 1
of 225 surveyed U.S. NAR-member agents use AI now or plan to.
Adoption is no longer the hard question. Trust is: 63% named output accuracy as a top concern and 49% named compliance or legal issues in the same n=225 survey. HomieBench is built around completed, reviewable jobs—not impressive chat demos. NAR / RPR survey
Best AI models for real estate agents in 2026
Quality, reliability, browser use, and completed-job economics are different questions. These v3 scores are scenario projections calibrated to one shared realtor task map and clearly separated from completed identical-harness runs.
Kimi K3
The v3 leader across the full realtor workflow mix, with a 96.6 projected score.
Kimi K3
Projected first for showing booking, CRM management, MLS work, and offer assembly.
Kimi K3
Projected first after balancing direct AI spend, finished-work quality, and human review burden.
Claude Fable 5
Still projected ahead on marketing quality and nuanced high-stakes realtor judgment.
Change the job. Watch the ranking change.
- 1Kimi K3 NewMoonshot AIScenario projectionOverall + value leader96.6out of 100
- 2Claude Fable 5AnthropicScenario projectionJudgment leader95.5out of 100
- 3GPT-5.6 SolOpenAIScenario projectionWorkflow leader95.4out of 100
- 4Claude Sonnet 5AnthropicScenario projectionBalanced94.3out of 100
- 5Muse Spark 1.1MetaScenario projectionNew value91.1out of 100
- 6Gemini 3.5 FlashGoogleScenario projectionFast value90.9out of 100
- 7Grok 4.5SpaceXAIScenario projectionAgentic value90.0out of 100
- 8GLM-5.2Z.aiScenario projectionOpen weight85.6out of 100
Changing the job changes the order. That is the point: the best model for offer strategy is not automatically the best model for showing coordination, content, or cost.
| Model | Overall | Lead generation & prospecting | CRM & client communications | Marketing & content | Showings & coordination | Property, market & document intelligence | Offers & negotiation | Transactions, closings & compliance | Back office & client deliverables |
|---|---|---|---|---|---|---|---|---|---|
| Kimi K3 | 96.6 | 95 | 98 | 94 | 99 | 97 | 98 | 94 | 97 |
| Claude Fable 5 | 95.5 | 94 | 94 | 96 | 94 | 96 | 97 | 96 | 96 |
| GPT-5.6 Sol | 95.4 | 94 | 96 | 93 | 97 | 95 | 95 | 97 | 95 |
| Claude Sonnet 5 | 94.3 | 92 | 94 | 95 | 95 | 94 | 94 | 95 | 95 |
| Muse Spark 1.1 | 91.1 | 90 | 92 | 91 | 94 | 91 | 89 | 90 | 93 |
| Gemini 3.5 Flash | 90.9 | 89 | 91 | 91 | 92 | 93 | 89 | 90 | 92 |
| Grok 4.5 | 90.0 | 90 | 91 | 90 | 93 | 89 | 88 | 88 | 93 |
| GLM-5.2 | 85.6 | 85 | 86 | 85 | 88 | 87 | 84 | 83 | 88 |
Which AI is best for each real estate workflow?
A strong realtor AI assistant should route the job instead of asking one model to be the best researcher, copywriter, coordinator, analyst, and negotiator at once.
Browser + multi-tool work
Showing booking, CRM management, MLS and property research, offer assembly, and long multi-step tool execution.
High-stakes judgment
Nuanced negotiation strategy, polished client work, marketing judgment, and decisions where subtlety matters.
Closings + compliance
Reliable transaction follow-through, deadline tracking, structured outputs, and compliance-sensitive workflows.
Why Kimi K3 leads realtor browser tasks in HomieBench v3
Kimi K3’s official 1M-token context, native visual understanding, structured output, dynamic tool loading, and tool-choice controls create a strong prior for long browser-and-system workflows. That matters when an AI must move from MLS research to a CRM record, showing request, document, or offer package without losing state.
The forecast is deliberately not a sweep. Fable 5 remains ahead in marketing and subtle client-facing judgment, while GPT-5.6 Sol remains ahead in closings and compliance. Kimi wins the weighted overall mix because realtors do a lot of tool-mediated work.
| Realtor browser task | Kimi K3 | Fable 5 | Kimi lead |
|---|---|---|---|
| Showing booking & coordination | 99 | 94 | +5 |
| CRM management & communications | 98 | 94 | +4 |
| MLS, property & document work | 97 | 96 | +1 |
| Offer writing & assembly | 98 | 97 | +1 |
How every model ranks across the eight realtor job families
Each bubble is one model’s projected category score. For priced models, area adds a model-level provider list-price estimate.
Higher dots mean higher projected quality. Each model keeps the same bubble size in every category: area shows its average single-pass provider list-price estimate across the six sample jobs—not that category’s task cost, tools, retries, subscriptions, or Homies effective cost. GLM-5.2 is outlined and not size-scaled because self-hosting cost varies. Hover or focus a dot to see its model and values.
- Kimi K3
- Fable 5
- GPT-5.6
- Sonnet 5
- Muse 1.1
- Gemini 3.5
- Grok 4.5
- GLM-5.2
Swipe to explore all eight categories →
Bubble area uses each model’s average provider list-price estimate across the six published sample jobs. It excludes tools, retries, subscription allocation, and human rescue; it is not observed completed-job cost.
| Category | Model | Projected score | Average single-pass provider list-price estimate across six sample jobs |
|---|---|---|---|
| Lead generation & prospecting | Kimi K3 | 95 | $1.17 |
| Lead generation & prospecting | Claude Fable 5 | 94 | $3.91 |
| Lead generation & prospecting | GPT-5.6 Sol | 94 | $2.21 |
| Lead generation & prospecting | Claude Sonnet 5 | 92 | $0.782 |
| Lead generation & prospecting | Muse Spark 1.1 | 90 | $0.388 |
| Lead generation & prospecting | Gemini 3.5 Flash | 89 | $0.662 |
| Lead generation & prospecting | Grok 4.5 | 90 | $0.580 |
| Lead generation & prospecting | GLM-5.2 | 85 | Variable self-hosted cost |
| CRM & client communications | Kimi K3 | 98 | $1.17 |
| CRM & client communications | Claude Fable 5 | 94 | $3.91 |
| CRM & client communications | GPT-5.6 Sol | 96 | $2.21 |
| CRM & client communications | Claude Sonnet 5 | 94 | $0.782 |
| CRM & client communications | Muse Spark 1.1 | 92 | $0.388 |
| CRM & client communications | Gemini 3.5 Flash | 91 | $0.662 |
| CRM & client communications | Grok 4.5 | 91 | $0.580 |
| CRM & client communications | GLM-5.2 | 86 | Variable self-hosted cost |
| Marketing & content | Kimi K3 | 94 | $1.17 |
| Marketing & content | Claude Fable 5 | 96 | $3.91 |
| Marketing & content | GPT-5.6 Sol | 93 | $2.21 |
| Marketing & content | Claude Sonnet 5 | 95 | $0.782 |
| Marketing & content | Muse Spark 1.1 | 91 | $0.388 |
| Marketing & content | Gemini 3.5 Flash | 91 | $0.662 |
| Marketing & content | Grok 4.5 | 90 | $0.580 |
| Marketing & content | GLM-5.2 | 85 | Variable self-hosted cost |
| Showings & coordination | Kimi K3 | 99 | $1.17 |
| Showings & coordination | Claude Fable 5 | 94 | $3.91 |
| Showings & coordination | GPT-5.6 Sol | 97 | $2.21 |
| Showings & coordination | Claude Sonnet 5 | 95 | $0.782 |
| Showings & coordination | Muse Spark 1.1 | 94 | $0.388 |
| Showings & coordination | Gemini 3.5 Flash | 92 | $0.662 |
| Showings & coordination | Grok 4.5 | 93 | $0.580 |
| Showings & coordination | GLM-5.2 | 88 | Variable self-hosted cost |
| Property, market & document intelligence | Kimi K3 | 97 | $1.17 |
| Property, market & document intelligence | Claude Fable 5 | 96 | $3.91 |
| Property, market & document intelligence | GPT-5.6 Sol | 95 | $2.21 |
| Property, market & document intelligence | Claude Sonnet 5 | 94 | $0.782 |
| Property, market & document intelligence | Muse Spark 1.1 | 91 | $0.388 |
| Property, market & document intelligence | Gemini 3.5 Flash | 93 | $0.662 |
| Property, market & document intelligence | Grok 4.5 | 89 | $0.580 |
| Property, market & document intelligence | GLM-5.2 | 87 | Variable self-hosted cost |
| Offers & negotiation | Kimi K3 | 98 | $1.17 |
| Offers & negotiation | Claude Fable 5 | 97 | $3.91 |
| Offers & negotiation | GPT-5.6 Sol | 95 | $2.21 |
| Offers & negotiation | Claude Sonnet 5 | 94 | $0.782 |
| Offers & negotiation | Muse Spark 1.1 | 89 | $0.388 |
| Offers & negotiation | Gemini 3.5 Flash | 89 | $0.662 |
| Offers & negotiation | Grok 4.5 | 88 | $0.580 |
| Offers & negotiation | GLM-5.2 | 84 | Variable self-hosted cost |
| Transactions, closings & compliance | Kimi K3 | 94 | $1.17 |
| Transactions, closings & compliance | Claude Fable 5 | 96 | $3.91 |
| Transactions, closings & compliance | GPT-5.6 Sol | 97 | $2.21 |
| Transactions, closings & compliance | Claude Sonnet 5 | 95 | $0.782 |
| Transactions, closings & compliance | Muse Spark 1.1 | 90 | $0.388 |
| Transactions, closings & compliance | Gemini 3.5 Flash | 90 | $0.662 |
| Transactions, closings & compliance | Grok 4.5 | 88 | $0.580 |
| Transactions, closings & compliance | GLM-5.2 | 83 | Variable self-hosted cost |
| Back office & client deliverables | Kimi K3 | 97 | $1.17 |
| Back office & client deliverables | Claude Fable 5 | 96 | $3.91 |
| Back office & client deliverables | GPT-5.6 Sol | 95 | $2.21 |
| Back office & client deliverables | Claude Sonnet 5 | 95 | $0.782 |
| Back office & client deliverables | Muse Spark 1.1 | 93 | $0.388 |
| Back office & client deliverables | Gemini 3.5 Flash | 92 | $0.662 |
| Back office & client deliverables | Grok 4.5 | 93 | $0.580 |
| Back office & client deliverables | GLM-5.2 | 88 | Variable self-hosted cost |
Lead generation & prospecting
Finding, prioritizing, qualifying, nurturing, and booking the right buyer and seller opportunities.
Build a compliant 30-day reactivation campaign for 200 past clients and cold leads, prioritize the call list, and create CRM tasks.
CRM & client communications
Keeping the database clean, the pipeline current, and every client conversation accurate and useful.
Deduplicate 80 contacts, reconstruct the relationship history, assign the right stage and next action, and draft today’s follow-up.
Marketing & content
Creating accurate listing marketing and on-brand social, email, video, advertising, and nurture content.
Turn a verified listing brief into MLS remarks, brochure copy, a landing page, a five-post social campaign, and a reel script.
Showings & coordination
Scheduling tours, optimizing routes, coordinating listing offices and trades, and keeping every party informed.
Fit six properties into a Saturday tour, respect notice rules and drive time, book the offices, and send the final itinerary.
Property, market & document intelligence
Researching properties and markets, building valuations, and reviewing inspections, title, zoning, HOA, and condo records.
Review the listing, comps, inspection, status certificate, minutes, budget, and reserve study; produce a sourced buyer risk brief.
Offers & negotiation
Structuring, drafting, explaining, comparing, presenting, countering, and negotiating offers under agent approval.
Prepare a competitive buyer offer, calculate every deadline, explain the trade-offs, and draft a negotiation plan with fallback positions.
Transactions, closings & compliance
Managing conditions, escrow/deposits, lenders, lawyers, title, insurance, walkthroughs, privacy, and compliance.
Turn the accepted offer into a closing ledger, assign every condition and deadline, and prepare the lender, lawyer, and client updates.
Back office & client deliverables
Organizing files, extracting documents, preparing signatures, coordinating collaborators, and building reports and presentations.
Audit the transaction file, organize and rename every document, identify missing items, and build a client-ready status deck.
The model is the brain. The Homies harness is the toolbox.
Models do the reasoning. Homies gives them the real-estate context, tools, memory, permissions, and review gates needed to finish the job. Holding that toolbox constant is the only useful way to compare the engines.
One realtor toolbox. Any reasoning engine.
The HomieBench design gives every model the same real estate context, tools, and safeguards, then measures the finished work it can produce.
The reasoning engine
The model interprets the request, reasons through the case, and decides which tool to use next.
- Kimi K3
- Claude Fable 5
- GPT-5.6 Sol
- Claude Sonnet 5
- Muse Spark 1.1
- Gemini 3.5 Flash
- Grok 4.5
- GLM-5.2
The realtor toolbox
The harness supplies the data access, integrations, memory, and operating rules that turn a smart answer into completed real estate work.
- CRM
- Property data
- Calendar
- Documents
- Research
- Calculator
- Publishing
- Real estate context
- Durable memory
- Permissions
- Review gates
Finished work, not chat
The agent approves advice, commitments, and anything client-facing before it goes out.
- CRM updated and follow-up drafted
- Showing tour booked and confirmed
- CMA and listing presentation ready
- Offer written, summarized, and flagged
- Property campaign packaged for approval
A brilliant model without the right property data, forms, CRM context, tools, and authority limits can still produce unusable work. A strong harness makes the work grounded, repeatable, reviewable, and connected to the agent’s actual business.
Our companion research paper defines the nine components of a production AI harness and the four operating levels a realtor can run it at. Most individual agents belong at Level 1 or 2, where consequential work still clears human approval.
What is an AI harness? The realtor’s guideThe cheapest tokens are rarely the cheapest offer, showing, or CMA
HomieBench v3 estimates direct AI and incremental tool spend per successful production-sized realtor task. Human verification remains essential, but its labour value is disclosed separately instead of being hidden inside the cents-per-task figure.
Estimated AI cost per offer, showing, CMA, MLS brief, and CRM follow-up
These headline numbers estimate direct model and incremental tool spend for a successful production-sized run, including retry risk. Human review time is shown separately and is not added to the cents-per-task figure.
- Projected overall leader
- Kimi K3
- 96.6 / 100 across 8 job families
- Browser + tool score
- 98.0
- CRM, showings, MLS/property work, and offer assembly
- Average direct AI cost
- $0.15
- Model + incremental tools across the five representative outcomes below
| Rank and model | Overall | Value index | $ / CRM follow-up | $ / Showing booked | $ / MLS brief | $ / Offer written | $ / CMA completed | Average |
|---|---|---|---|---|---|---|---|---|
1Kimi K3Best valueMoonshot AI | 96.6 | 100 | $0.04 | $0.08 | $0.14 | $0.18 | $0.33 | $0.15 |
2GPT-5.6 SolOpenAI | 95.4 | 78 | $0.07 | $0.12 | $0.23 | $0.32 | $0.56 | $0.26 |
3Claude Fable 5Anthropic | 95.5 | 74 | $0.12 | $0.21 | $0.40 | $0.55 | $0.99 | $0.45 |
4Claude Sonnet 5Anthropic | 94.3 | 69 | $0.03 | $0.06 | $0.11 | $0.14 | $0.24 | $0.12 |
5Gemini 3.5 FlashGoogle | 90.9 | 53 | $0.03 | $0.05 | $0.09 | $0.13 | $0.21 | $0.10 |
6Muse Spark 1.1Meta | 91.1 | 52 | $0.02 | $0.04 | $0.07 | $0.09 | $0.16 | $0.08 |
7Grok 4.5SpaceXAI | 90.0 | 46 | $0.03 | $0.05 | $0.10 | $0.12 | $0.22 | $0.10 |
—GLM-5.2Z.ai | 85.6 | Variable | Variable | Variable | Variable | Variable | Variable | Variable |
Headline formula: (published model token cost + incremental per-run tool charges) ÷ projected successful completion. Production-sized prompts are used here, not the much larger benchmark case files. The value index separately combines projected overall quality with the fully loaded cost of review time valued at $60/hour, then normalizes the leader to 100.
Human verification remains necessary. It is modeled separately at approximately 1–7 minutes for Kimi K3 across these tasks and valued internally at $60/hour, but is not included in the displayed AI cost. Also excludes fixed CRM, MLS, showing-platform, forms, signatures, subscriptions, taxes, and enterprise support.
The value frontier
Projected quality vs. loaded cost per completed outcome
| Model | Projected overall score out of 100 | Average loaded cost per completed outcome | Value index (leader = 100) |
|---|---|---|---|
| Kimi K3 | 96.6 | $3.71 | 100 |
| GPT-5.6 Sol | 95.4 | $4.71 | 78 |
| Claude Fable 5 | 95.5 | $4.94 | 74 |
| Claude Sonnet 5 | 94.3 | $5.24 | 69 |
| Gemini 3.5 Flash | 90.9 | $6.64 | 53 |
| Muse Spark 1.1 | 91.1 | $6.75 | 52 |
| Grok 4.5 | 90.0 | $7.58 | 46 |
Human review burden
Average human review minutes per completed outcome
- Kimi K3
- 3.6 min
- GPT-5.6 Sol
- 4.5 min
- Claude Fable 5
- 4.5 min
- Claude Sonnet 5
- 5.1 min
- Gemini 3.5 Flash
- 6.5 min
- Muse Spark 1.1
- 6.7 min
- Grok 4.5
- 7.5 min
Provider list price and Homies effective cost are still separate questions
List price is one input; the access route decides the rest. The explorer below keeps the two views separate, and the complete real estate AI integration stack maps which realtor systems those per-run tool calls actually reach.
A directional grade—not a measured dollar result—based on connected-plan allocation, limits, retries, and tool fees.
- #1Kimi K3
Projected first-pass completion and browser/tool efficiency offset its mid-tier token price.
A+qualitative grade - #2GPT-5.6 Sol
Strong connected-account economics and the projected reliability leader for closing workflows.
Aqualitative grade - #3Gemini 3.5 Flash
Strong price-performance prior for high-volume multimodal support work.
Aqualitative grade - #4Muse Spark 1.1
Strong agentic prior with lower reported pricing than Grok 4.5.
Aqualitative grade - #5Grok 4.5
Efficient agentic route, but pricier than Muse on the reported launch card.
B+qualitative grade - #6Claude Sonnet 5
Strong quality-to-cost balance, subject to post-intro pricing.
Bqualitative grade - #7Claude Fable 5
Premium route reserved for high-consequence judgment.
Dqualitative grade - —GLM-5.2
Infrastructure, utilization, support, and hosting choices determine cost.
Variablequalitative grade
How Homies frames effective cost
(allocated plan cost + metered overage + tool fees + retry spend) ÷ successful jobs
Kimi K3 ranks first in this qualitative v3 estimate because its projected first-pass completion and browser/tool efficiency offset its mid-tier token price. GPT-5.6 remains a strong connected-account route. OAuth authenticates a connection; it does not make inference free. Plan fees, limits, overages, and separate API billing still apply.
Provider prices updated July 16, 2026. Kimi K3 uses Moonshot AI’s published $3 input / $15 output per million-token cache-miss pricing. Muse Spark 1.1 pricing is launch reporting pending confirmation in the Meta console. Claude Sonnet 5 uses its introductory rate. Taxes, regional pricing, search/tool charges, and subscription fees are excluded from token-only examples.
What is inside all 100 HomieBench workflows?
The headline categories stay simple. Underneath them is the real work of running a real estate business—from the first lead to years after closing, with the files, trades, deadlines, and client judgment in between.
Lead generation & prospecting
Finding, prioritizing, qualifying, nurturing, and booking the right buyer and seller opportunities.
CRM & client communications
Keeping the database clean, the pipeline current, and every client conversation accurate and useful.
Marketing & content
Creating accurate listing marketing and on-brand social, email, video, advertising, and nurture content.
Showings & coordination
Scheduling tours, optimizing routes, coordinating listing offices and trades, and keeping every party informed.
Property, market & document intelligence
Researching properties and markets, building valuations, and reviewing inspections, title, zoning, HOA, and condo records.
Offers & negotiation
Structuring, drafting, explaining, comparing, presenting, countering, and negotiating offers under agent approval.
Transactions, closings & compliance
Managing conditions, escrow/deposits, lenders, lawyers, title, insurance, walkthroughs, privacy, and compliance.
Back office & client deliverables
Organizing files, extracting documents, preparing signatures, coordinating collaborators, and building reports and presentations.
Every workflow in the HomieBench map
Open a family to inspect every task and its review level. High-stakes work must clear human approval and all critical criteria.
01Lead generation & prospecting13 workflows · 10% of quality score
| Workflow | What the agent must finish | Review level |
|---|---|---|
| Lead-source import | Import leads from portals, ads, open houses, referrals, and spreadsheets without losing source data. | Routine |
| Ideal-client profile | Define the audience, geography, property type, motivation, and qualification signals for a campaign. | Review required |
| Farm-area prospect list | Build a prioritized geographic farm list with reasons and a compliant next action. | Review required |
| Seller-intent signals | Identify contacts showing plausible move, equity, life-event, or engagement signals without inventing facts. | Review required |
| Buyer-intent signals | Prioritize buyers by activity, timeframe, financing readiness, and property fit. | Review required |
| Expired-listing outreach | Research an expired listing and prepare a compliant, personalized multi-touch approach. | Review required |
| FSBO outreach | Prepare respectful owner outreach, value framing, discovery questions, and follow-up timing. | Review required |
| Past-client reactivation | Find dormant relationships and create a useful re-engagement reason such as an equity or CMA update. | Routine |
| Database nurture segments | Group contacts by relationship, intent, timing, market, and next-best campaign. | Routine |
| Outbound call list and script | Prioritize a daily call list and draft context-aware openings, questions, and voicemail. | Review required |
| Multi-channel prospecting sequence | Create coordinated email, SMS, call, and social touches with timing and stop rules. | Review required |
| Lead qualification and score | Assess motivation, agency status, timeframe, financing, fit, and follow-up urgency. | Review required |
| Appointment setting and handoff | Offer suitable times, book the meeting, create the CRM event, and prepare the agent brief. | Review required |
02CRM & client communications13 workflows · 15% of quality score
| Workflow | What the agent must finish | Review level |
|---|---|---|
| Contact deduplication | Merge duplicate people and households while preserving attribution, notes, consent, and history. | Routine |
| Contact enrichment | Structure known preferences, relationships, properties, and communication details without guessing. | Review required |
| Conversation summarization | Turn calls, emails, and messages into a factual timeline, decisions, concerns, and next actions. | Routine |
| Lifecycle and stage classification | Place contacts and opportunities in the correct stage using explicit evidence. | Routine |
| Next-best action | Recommend the most useful next step, owner, channel, and due date for each relationship. | Review required |
| Inbound inquiry response | Draft a fast, helpful reply that answers known facts, asks useful questions, and avoids commitments. | Review required |
| Buyer discovery brief | Capture needs, trade-offs, financing, timing, decision-makers, and search boundaries. | Review required |
| Seller discovery brief | Capture motivation, property context, timing, condition, expectations, and decision criteria. | Review required |
| Client email drafting | Write clear, accurate, on-brand email from CRM and transaction context. | Review required |
| Client SMS drafting | Write concise, context-aware text messages with correct tone and no invented promises. | Review required |
| Long-term nurture plan | Create relationship-first follow-up that stays useful across a long buying or selling horizon. | Review required |
| Objection response | Prepare calibrated responses to fee, timing, pricing, competition, and process objections. | High stakes |
| Pipeline health report | Summarize conversion risk, stalled opportunities, overdue work, and coaching priorities. | Routine |
03Marketing & content13 workflows · 10% of quality score
| Workflow | What the agent must finish | Review level |
|---|---|---|
| MLS remarks | Draft accurate, compliant public remarks from verified property facts and approved positioning. | Review required |
| Property highlight sheet | Turn features, improvements, rooms, and lifestyle context into a scannable fact sheet. | Review required |
| Listing brochure | Build structured brochure copy, hierarchy, calls to action, and proof points in the agent brand. | Review required |
| Listing landing page | Create the page outline, property story, feature modules, lead capture, and SEO copy. | Review required |
| Property email campaign | Draft announcement, open-house, update, and follow-up emails for the right audience. | Review required |
| Social content calendar | Plan useful listing, market, education, community, and personal-brand posts. | Routine |
| Social captions | Create platform-aware captions, hooks, calls to action, and compliant hashtags. | Review required |
| Carousel creation | Turn a market insight or property story into a clear slide-by-slide social carousel. | Review required |
| Reel and video script | Write short-form and long-form real estate video scripts with shots, hooks, and captions. | Review required |
| Paid-ad campaign | Build audience, creative angle, copy variants, landing-page match, and measurement plan. | High stakes |
| Brand-voice rewrite | Adapt content to the agent's approved tone without changing facts or compliance meaning. | Routine |
| Newsletter production | Assemble market, listing, client, and community content into a useful recurring newsletter. | Review required |
| Performance repurposing | Analyze approved content performance and turn strong ideas into new channel-native assets. | Routine |
04Showings & coordination12 workflows · 10% of quality score
| Workflow | What the agent must finish | Review level |
|---|---|---|
| Showing availability plan | Reconcile client, agent, property, notice, occupancy, and travel constraints. | Review required |
| Listing-office showing request | Prepare or place the authorized request with correct party, property, time, and conditions. | Review required |
| Tour route optimization | Order properties for drive time, appointment windows, breaks, and client priorities. | Routine |
| Tour confirmation package | Send the itinerary, access notes, property links, timing, and preparation reminders. | Review required |
| Showing reschedule | Resolve conflicts, re-contact parties, update calendars, and preserve the rest of the route. | Review required |
| Showing feedback | Collect, summarize, and route useful buyer feedback without exposing confidential information. | Review required |
| Open-house operations | Prepare schedule, signage, registration, safety, follow-up, and seller reporting. | Review required |
| Calendar blocking | Create accurate appointments, buffers, travel time, reminders, and linked records. | Routine |
| Vendor booking | Coordinate approved photographers, stagers, cleaners, contractors, and measurements. | Review required |
| Inspection coordination | Book the inspector, align parties, share access instructions, and track the report. | High stakes |
| Appraisal access | Coordinate appraisal timing, property access, contacts, and the approved information package. | Review required |
| Client tour brief | Prepare a concise mobile itinerary with property fit, verified facts, questions, and flags. | Review required |
05Property, market & document intelligence13 workflows · 15% of quality score
| Workflow | What the agent must finish | Review level |
|---|---|---|
| Listing fact verification | Extract and reconcile facts across the listing, tax record, disclosures, and source documents. | High stakes |
| Neighbourhood research | Prepare sourced context on amenities, mobility, housing, plans, and client-relevant trade-offs. | Review required |
| Market trend report | Analyze inventory, absorption, pricing, days on market, and segment-level movement. | Review required |
| Comparable selection | Choose defensible sold, active, expired, and leased comps with inclusion reasons. | High stakes |
| Comparable adjustments | Adjust for time, size, condition, lot, parking, features, and location with uncertainty. | High stakes |
| CMA production | Build the evidence table, pricing range, positioning narrative, and seller-ready report. | High stakes |
| Home evaluation | Estimate a value range, confidence, key drivers, missing data, and next validation steps. | High stakes |
| Investor analysis | Model revenue, expenses, financing, cash flow, cap rate, sensitivity, and risks. | High stakes |
| Rental estimate | Select rental evidence, adjust for features and timing, and explain a supportable range. | High stakes |
| Zoning and permit research | Find applicable zoning, permits, constraints, and questions for the right authority. | High stakes |
| Tax, title, and survey review | Summarize source documents, inconsistencies, easements, boundaries, and referral questions. | High stakes |
| HOA and condo document review | Review bylaws, minutes, budgets, reserves, fees, insurance, restrictions, and litigation signals. | High stakes |
| Home-inspection review | Summarize findings by urgency, cost uncertainty, specialist need, and negotiation relevance. | High stakes |
06Offers & negotiation12 workflows · 15% of quality score
| Workflow | What the agent must finish | Review level |
|---|---|---|
| Buyer offer strategy | Translate goals, competition, financing, risk tolerance, and property facts into a strategy. | High stakes |
| Term recommendation | Recommend price, deposit, closing, inclusions, conditions, and expiry with trade-offs. | High stakes |
| Clause selection | Choose only broker-approved clauses that match instructions, jurisdiction, and deal facts. | High stakes |
| Deadline calculation | Calculate expiry, condition, deposit, notice, and closing dates with calendar rules. | High stakes |
| Deposit and closing plan | Check deposit mechanics, funding timing, closing feasibility, and client explanation. | High stakes |
| Offer drafting | Prepare a review-ready purchase or lease offer from verified instructions and approved forms. | High stakes |
| Buyer offer explanation | Explain terms, obligations, risks, alternatives, and approval points in plain language. | High stakes |
| Seller offer summary | Present price, terms, conditions, timing, risks, and net implications without hiding trade-offs. | High stakes |
| Multiple-offer comparison | Normalize offers side by side and flag material differences, gaps, and decision points. | High stakes |
| Counteroffer drafting | Prepare the approved changes, rationale, timing, and client/counterparty communication. | High stakes |
| Negotiation plan | Map priorities, leverage, concessions, signals, limits, and fallback paths for agent approval. | High stakes |
| Amendment and waiver support | Track the requested change, authority, form, dates, dependencies, and signature status. | High stakes |
07Transactions, closings & compliance12 workflows · 15% of quality score
| Workflow | What the agent must finish | Review level |
|---|---|---|
| Accepted-offer extraction | Turn the executed agreement into parties, dates, conditions, obligations, and a deal ledger. | High stakes |
| Condition and contingency tracker | Track each requirement, responsible party, evidence, deadline, and escalation path. | High stakes |
| Escrow and deposit tracking | Monitor instructions, receipt, trust/escrow status, deadlines, and exceptions without moving funds. | High stakes |
| Financing coordination | Prepare the lender package, track approval steps, surface gaps, and keep parties aligned. | High stakes |
| Appraisal issue brief | Summarize a valuation gap, contract implications, options, and questions for licensed advisers. | High stakes |
| Inspection resolution | Convert findings into specialist referrals, repair/credit options, deadlines, and client decisions. | High stakes |
| Lawyer, title, and insurance liaison | Share the approved package, track questions, and route issues to the right professional. | High stakes |
| Closing timeline | Create a dated plan for financing, legal, insurance, utilities, movers, walkthrough, and keys. | High stakes |
| Final walkthrough | Prepare the checklist, evidence capture, deficiency routing, and urgent escalation plan. | High stakes |
| Key handover and post-close | Coordinate possession, keys, closing communication, record updates, and relationship follow-up. | Review required |
| Fair-housing and advertising review | Flag protected-class targeting, steering, exclusionary language, and risky claims. | High stakes |
| Privacy and record-retention review | Minimize sensitive data, apply permissions, and check storage, sharing, and retention rules. | High stakes |
08Back office & client deliverables12 workflows · 10% of quality score
| Workflow | What the agent must finish | Review level |
|---|---|---|
| File organization | Name, classify, link, deduplicate, and place documents in the correct client and transaction folders. | Routine |
| Inbox triage | Separate urgent client/deal work, replies, waiting items, FYI, and low-value noise. | Routine |
| Calendar and task administration | Create owners, due dates, reminders, dependencies, and recurring operational work. | Routine |
| Document extraction | Pull parties, properties, dates, amounts, clauses, signatures, and missing fields into structured records. | Review required |
| Template population | Fill approved letters, checklists, reports, and forms from verified source data. | Review required |
| Signature-package preparation | Assemble documents, recipient order, fields, instructions, and approval checkpoints. | High stakes |
| Transaction file audit | Check required documents, signatures, dates, disclosures, evidence, and unresolved exceptions. | High stakes |
| Team SOP and handoff | Convert recurring work into a clear owner, trigger, procedure, evidence, and escalation path. | Routine |
| Collaborator liaison brief | Prepare context and questions for inspectors, lawyers, lenders, appraisers, stagers, and trades. | Review required |
| Listing presentation | Build the market story, pricing plan, launch strategy, proof, timeline, and seller objections. | High stakes |
| Client advisory deck | Turn research and decisions into a sourced, branded presentation for agent review. | High stakes |
| Business analytics and coaching | Analyze activity, conversion, pipeline, source ROI, capacity, and next-week priorities. | Review required |
How HomieBench evaluates AI on real estate work
The v3 design gives each model the same full assignment in a realistic workspace, then grades the finished deliverable against atomic criteria. A correct-looking paragraph is not enough.
A real assignment
A short broker-style instruction asks for finished work, not a trivia answer or a perfect prompt.
A controlled case file
Each run receives the same clients, properties, CRM history, messages, comps, forms, and distractor documents.
The same Homies harness
Models get the same tools, context, permissions, memory rules, budgets, and approval boundaries.
Reviewable work product
The output must be something an agent can inspect and use: a CMA, offer, CRM update, tour, campaign, or closing brief.
Atomic grading
Deterministic checks, a blinded first-pass judge, and real-estate review score every required fact and decision.
Weighted scorecard
A model can write beautifully and still fail the job. Accuracy, completion, professional judgment, compliance, and tool use carry almost all the weight.
Automatic hard fails
- Invents a comp, listing fact, document term, or client instruction
- Makes a discriminatory recommendation or enables steering against a protected class
- Sends, signs, publishes, books, or claims to act without the required authority
- Presents legal, tax, lending, inspection, or other licensed advice as certain
- Misses or miscalculates a material deadline, amount, condition, or obligation
- Exposes private client or transaction information beyond the minimum required
- Omits a critical risk or required deliverable while presenting the job as complete
Private holdout
Evaluation cases stay private to reduce prompt-tuning and benchmark overfitting.
Blinded review
Model identity should be hidden from graders, with agreement tracked on subjective criteria.
Repeated runs
Final releases should publish completion, rescue rate, reliability, cost, and latency.
Limits, model versions, and source notes
A trustworthy benchmark shows where the certainty stops. The July table is useful directional editorial evidence, not a substitute for raw run logs.
Editorial forecast · ±3 points
All seven July placements are editorial priors based on provider evidence, historical model behavior, realtor-task fit, and the published scoring design—not completed runs. Treat differences under three points as ties until identical-harness outputs and grader records are published.
Pricing snapshot
Provider pricing and availability can change quickly. Public API price is kept separate from the effective cost of Homies’ own access route.
Jurisdiction and advice
Tasks model North American residential brokerage work. Forms, disclosure, privacy, fair housing, agency, and legal requirements vary by market.
Models are only one layer
This compares reasoning engines inside one harness—not complete realtor products, implementation quality, security, data licensing, or support.
Primary model, benchmark, and industry sources
AI for realtors, in plain English
Short answers to the questions agents and brokerages ask before trusting AI with real work.
What is the best AI for realtors in 2026?
HomieBench v3 projects Kimi K3 as the best overall AI model for realtor work and the strongest completed-job cost/benefit option. It leads the browser-heavy categories—CRM management, showing coordination, MLS and property work, offer assembly, and back-office execution—but not every category. Claude Fable 5 remains the projected marketing and nuanced-judgment leader, while GPT-5.6 Sol leads transactions, closings, and compliance.
Is Kimi K3, ChatGPT, or Claude better for real estate agents?
It depends on the job. HomieBench v3 projects Kimi K3 as the strongest overall browser-and-tool model, Claude Fable 5 as the best choice for polished marketing and subtle professional judgment, and GPT-5.6 Sol as the reliability leader for closing and compliance workflows. A realtor AI platform should route among them instead of forcing one engine onto every assignment.
Can AI write a real estate offer?
AI can help assemble terms, calculate deadlines, draft approved clauses, summarize trade-offs, and prepare a review-ready offer package. A licensed real estate professional must verify local forms, legal requirements, client instructions, and every binding commitment before anything is signed or sent.
Can AI create a CMA or home evaluation?
AI can organize comparables, calculate adjustments, explain a price range, and build a client-ready CMA narrative when it has access to reliable property data. The agent remains responsible for comp selection, market judgment, data licensing, and the final pricing recommendation.
What is the cheapest AI model for realtors?
The cheapest token price is not necessarily the cheapest successful realtor outcome. Muse Spark 1.1 has the lowest reported standard token blend among the hosted models in this update, while Gemini 3.5 Flash can be cheaper on asynchronous tiers. HomieBench v3 projects Kimi K3 as the best completed-job value because stronger first-pass browser and tool execution reduces retries and human correction time. Subscription fees, limits, tools, data access, and overages still matter.
How does HomieBench estimate cost per offer, showing, CMA, or CRM update?
The v3 headline estimate combines published provider token pricing, production-sized input and output assumptions, incremental per-run tool charges, projected task completion, and retry risk. Human review time is disclosed separately and is not added to the displayed AI cost. The figures are directional estimates, not provider invoices or completed run logs, and exclude fixed CRM, MLS, showing-platform, forms, signatures, subscriptions, taxes, and enterprise support.
Is AI safe for real estate client and transaction data?
Only when the surrounding system enforces data minimization, permissions, approved integrations, retention rules, and human review. Model quality alone does not create a compliant workflow. Brokerages should review vendor terms, privacy controls, fair-housing obligations, local regulations, and their own policies before using AI with client data.
What is an AI harness, and how is it different from a chatbot?
The model is the reasoning engine. The harness is the toolbox around it: property and CRM context, memory, email and calendar access, document tools, calculators, permissions, workflow logic, and review gates. A chatbot mainly produces an answer; a capable harness can produce controlled, reviewable work.
Does Homies replace the real estate agent?
No. Homies is designed to work under agent review. It prepares research, drafts, updates, schedules, files, and client-ready deliverables so agents can spend more time advising, negotiating, building relationships, and making accountable professional decisions.
Related: the client and transaction data answer above is the short version of the RAILS governance framework, our whitepaper on capability-without-custody permissions, approvals, and audit trails for agentic AI in real estate.
Put the best AI models to work inside Homies.
One manager, a team of real-estate specialists, and the tools to turn requests into CMAs, offers, campaigns, follow-up, research, and client-ready work. You review what goes out.
HomieBench v3 · Published by Homies in partnership with Realist · Editorial forecast with ±3-point uncertainty until replaced by documented identical-harness runs.