Skip to content

Claude Haiku 5.5: real-world results

Claude Haiku 5.5 passed 363 of 410 runs (89%) on 403 different use cases.

Average cost per run was $0.01, average wall time 2m, with 0.33 human step-ins per run.

Ranked #1 for: creative / animated scene (one HTML file), creative / web animation, finance / retirement planning, Model ladder: fix 10 real merged bugs with tests hidden

Results by category

CategoryRunsPassed
Creative / Animated Scene (one HTML File)2424/24
Software & DevOps1817/18
Creative / Web Animation66/6
Finance / Retirement Planning44/4
Games & Simulations44/4
Finance / Accounts Payable31/3
Sales, Marketing & Support33/3
Travel & Bookings33/3
Analytics / Experiment Review22/2
Coding22/2
Data / Accounting22/2
Data Structures (JavaScript)22/2
data/CSV Analysis22/2
HR / Payroll22/2
Marine / Tides and Pilotage22/2
Operations / Scheduling22/2
Ops/debugging22/2
Privacy / Data Operations21/2
Protocol / Network Server22/2
Security Fix22/2
Spec-following Parser22/2
Writing With Rubric22/2
3D / Game Assets11/1
Accessibility11/1
Accounting / Bill Payment11/1
Accounting / Fixed Assets11/1
Algorithmic Optimisation With Perf Limit11/1
Algorithms / Package Management11/1
Algorithms / Routing11/1
Allotments / Lettings11/1
Analytics / Metrics11/1
Analytics / Reporting10/1
API Client From Spec11/1
Auto Repair / Estimate Authorisation10/1
Auto Repair / Invoicing11/1
Aviation / Crew Scheduling Compliance11/1
Bakery / Wholesale Invoicing11/1
Beekeeping / Harvest Ledger11/1
Car Wash / Fleet Bookings11/1
Careers / Job Search11/1
Catering / Invoicing11/1
Charity / Finance Admin11/1
Charity / Volunteer Logistics10/1
Charity Shop / Collections10/1
Childcare / Holiday Camp11/1
Childcare / Household Bills11/1
Chimney Sweep / Visit Bookings10/1
CLI Tool11/1
Climbing Wall / Session Bookings10/1
Clinic / Billing11/1
Clinic / Patient Intake11/1
Clinic / Scheduling11/1
Cloud / Cost11/1
Cloud Operations / Cost Control10/1
Code Security / Backend Review11/1
Coffee Roastery / Green Bean Buying11/1
Coffee Roastery / Roast Ledger11/1
Commercial Property / Service Charges11/1
Community / Local Clubs11/1
Community Hall / Bookings11/1
Community Lending / Bookings10/1
Community Transport / Bookings11/1
Community Transport / Volunteer Drivers11/1
Compliance / Records Management11/1
Concurrency Bug11/1
Construction / Scaffold Hire11/1
Consumer Protection / Scam Screening11/1
Content & Creative11/1
Cooking / Home11/1
Corporate Finance / Treasury11/1
Council / Parking Permits11/1
Courier / Pickup Bookings11/1
Courier / Rating11/1
Creative / Animation11/1
Creative / Data Visualisation11/1
Creative / Interactive Explainer Web App11/1
Customer Care / Refunds11/1
Customer Service / Warranty11/1
Customer Support / Refunds11/1
Customer Support / SLA Reporting11/1
Data / Reliability Metrics11/1
Data / Rules Engine11/1
Data / Time Series11/1
Data Cleaning / Entity Resolution11/1
Data Wrangling11/1
data/SQL11/1
Date/time Logic11/1
Debugging11/1
Debugging (flaky Tests / Nondeterminism)11/1
Debugging (JavaScript)11/1
Debugging / SQL11/1
Dental / Insurance Estimates11/1
Dental / Lab Ordering11/1
Dental / Treatment Bookings11/1
Dental Practice / Appointments10/1
Device Administration (ADB)11/1
DevOps / Configuration11/1
DevOps / Operations10/1
Distributed Systems / Hashing11/1
Doc-to-code Spec (binary Format)11/1
Document Extraction11/1
Document Extraction / Legal11/1
Driving School / Billing11/1
E-commerce / Shipping11/1
Ecommerce / Order Release10/1
Ecommerce / Returns11/1
Ecommerce / Subscriptions10/1
Education / Grading11/1
Education / Outdoor Activities11/1
Education / Printable Worksheets11/1
Escape Room / Game Bookings11/1
Events / Catering Headcount11/1
Events / Planning10/1
Facilities / Parking11/1
Facilities / Workplace Analytics11/1
Family Logistics / Personal Admin11/1
Family Support / Grants11/1
Farm Shop / Subscriptions11/1
Filesystem Audit / Cleanup Planning11/1
Finance / Backtesting11/1
Finance / Debt Payoff11/1
Finance / Debugging11/1
Finance / Employee Expenses11/1
Finance / Expense Audit11/1
Finance / Expense Claims11/1
Finance / Expenses11/1
Finance / Lending11/1
Finance / Loans11/1
Finance / Market Microstructure11/1
Finance / Portfolio11/1
Finance / Retirement Tax11/1
Finance / Revenue Reporting11/1
Finance / Statement Analysis11/1
Finance / Tax11/1
Finance / Valuation11/1
Finance Calc11/1
Fitness Studio / Bookings10/1
Fleet Management / Fuel Audit11/1
Fleet Operations / Maintenance10/1
Florist / Event Costing11/1
Florist / Event Order Confirmations10/1
Florist / Wholesale Ordering11/1
Food / Kitchen Hire11/1
Food Truck / Event Bookings10/1
Freelance / Invoicing11/1
Game Backend / Crash Reproduction and Fixing11/1
Garden Centre / Deliveries10/1
Git History Investigation11/1
Home Energy / Appliance Breakdown11/1
Home Energy / Install Bookings10/1
Home Energy / Plan Switching11/1
Home Lab / Privacy11/1
Home Network / Device Triage11/1
Home Services / Billing11/1
Hospitality / Front Office10/1
Hospitality / Payroll11/1
Hospitality / Revenue Accounting11/1
Hotel / Billing11/1
Household / Bill Splitting11/1
Household / Health Insurance11/1
Household / Shared Expenses11/1
Household / Subscriptions11/1
Household Finance / Bill Payments10/1
Household Finance / Insurance Renewal11/1
Household Finance / Spending Audit11/1
HR / Leave Administration11/1
HVAC / Maintenance Visit Booking10/1
HVAC / Service-call Invoicing11/1
Identity & Access Management11/1
Incremental Build / Cache Invalidation Bug11/1
Industrial Automation / PLC Programming11/1
Insurance / Claims Adjudication11/1
IT / DNS Administration10/1
IT / Identity and Access Management11/1
IT Asset Management / Licensing11/1
IT Support / Crash Diagnosis11/1
Job Search / Posting Shortlist11/1
Junior Football / Registrations11/1
Karting Track / Race Bookings11/1
Knowledge Work / Extraction11/1
Knowledge Work / Financial Analysis11/1
Knowledge Work / Technical Writing11/1
Landscaping / Job Invoicing11/1
Landscaping / Tree-work Scheduling10/1
Laundromat / Takings Reconciliation11/1
Law Firm / Docketing11/1
Law Firm / Matter Intake10/1
Learning / Study Notes11/1
Legal / Contract Review11/1
Legal Ops / Contract Management11/1
Leisure / Marina Berths11/1
Leisure Centre / Lesson Enrolments11/1
Lettings / Gas Safety11/1
Lettings / Repairs11/1
Library / Overdue Fines11/1
Library Services / Circulation11/1
Life Admin & Home11/1
Locksmith / Code Decoding10/1
Log Forensics (security Incident)11/1
Logistics / Shipping Quotes11/1
Long-context Needle11/1
Marine / Algorithms11/1
Marine / Anchoring11/1
Marine / Collision Avoidance11/1
Marine / Data Parsing11/1
Marine / Environmental Monitoring11/1
Marine / Fishing Compliance11/1
Marine / Fishing Planning11/1
Marine / Navigation11/1
Marine / Passage Planning11/1
Marine / Powerboat Planning11/1
Marine / Sailing Instruments11/1
Marine / Sailing Performance11/1
Marine / Sports Scoring11/1
Marine / Tides11/1
Marine / Weather Routing11/1
Market Research / Survey Analysis11/1
Marketing / Budget Allocation11/1
Marketing / Data Cleaning11/1
Marketing Operations / Consent Compliance11/1
Migration (SQL)11/1
Migration With Backward Compatibility11/1
Money, Bills & Benefits11/1
Multi-file JS Refactor11/1
Networking / Home Lab11/1
Numeric Precision11/1
Operations / Incident Triage11/1
Operations / Inventory11/1
Operations / Purchasing11/1
Optimization/scheduling11/1
Parsing / Evaluation11/1
Payroll / Hourly Staff11/1
Payroll / Time and Attendance11/1
Payroll / Timesheets11/1
People Analytics / Workforce Reporting11/1
Performance Optimization11/1
Personal Assistant / Voice Handoff11/1
Personal Finance / Investment Tax11/1
Personal Finance / Lending11/1
Personal Security / Read-only Audit11/1
Pet Boarding / Bookings10/1
Pet Care / Billing11/1
Pet Care / Dog Walking11/1
Pet Care / Small Business Bookings11/1
Pet Grooming / Appointment Confirmations10/1
Pet Grooming / Appointment Pricing11/1
Pharmacy / Home Deliveries11/1
Pharmacy Operations / Dispensing10/1
Piano Tuning / Visit Scheduling11/1
Picture Framing / Order Release10/1
Plumbing / Job Dispatch10/1
Plumbing / Job Invoicing11/1
Pottery Studio / Kiln Firing Ledger11/1
Print Shop / Meter Reconciliation11/1
Privacy / Document Drafting11/1
Privacy / Text Processing11/1
Procurement / Vendor Selection11/1
Productivity / Email11/1
Property / Short-term Lets11/1
Property / Storage Billing11/1
Property Management / Contractor Dispatch11/1
Property Management / Deposits11/1
Property Management / Maintenance10/1
Property Management / Maintenance Dispatch10/1
Radio Timekeeping / Signal Decoding11/1
Real Estate / Property Management11/1
Refactor11/1
Regex/parsing11/1
Removals / Job Scheduling11/1
Removals / Van Hire11/1
Rentals / Pricing11/1
Research Administration / Purchasing11/1
Research Synthesis (offline)11/1
Residents' Association / Parking11/1
Restaurant / Catering Bookings10/1
Restaurant / Kitchen Costing11/1
Retail / Inventory Planning11/1
Retail / Loyalty Programme Operations11/1
Retail / Pricing11/1
Retail / Stock Valuation11/1
Retail / Till Pricing11/1
Revenue / Pricing Operations10/1
Rideshare Driving / Offer Screening11/1
Robotics / Hardware Modelling11/1
Robotics / Spatial Planning11/1
Safe Autonomy / Device Administration11/1
Sales Operations / Compensation10/1
Sales Operations / Pipeline Hygiene10/1
Scheduling / Calendar11/1
School Office / Trip Bookings11/1
School Office / Trips11/1
Secondhand Bookshop / Code Decoding11/1
Security, Science & Hardware11/1
Self-hosting / Graph Planning11/1
Shell Scripting11/1
Shopping & Errands11/1
Small Business / Accounts Receivable11/1
Small Business / Credit Control11/1
Small Interpreter11/1
Smart Home / Visual UI11/1
Software / Calendar Parsing10/1
Software / Legacy Refactor11/1
Software / Refactor11/1
Software / Version Control11/1
Software QA / Pre-launch Bug Finding10/1
Software Reverse Engineering / App Internals11/1
Software Security / Dependency Triage11/1
Sports Administration / Competitions11/1
Sports Club / Kit Orders11/1
SQL (sqlite3 Triggers)11/1
SRE / Incident Analysis11/1
State Machine (JavaScript)11/1
State Machines / UI Logic11/1
Strategy / Portfolio Prioritisation11/1
Swimming School / Bookings11/1
Tailoring / Alteration Orders10/1
Taxi / Fare Audit11/1
Test Writing (mutation Testing)11/1
Text Processing / Tooling11/1
Tool-use Planning11/1
Tooling / Pattern Matching11/1
Travel / Compensation Claims11/1
Travel / Itinerary11/1
Travel / Rebooking11/1
Tuition / Billing11/1
Unicode / Text Normalization11/1
Upholstery Workshop / Fabric Ordering11/1
Upholstery Workshop / Job Billing11/1
Utilities / Metering and Billing10/1
Validation / Spec Implementation11/1
Vehicles / Diagnostics11/1
Veterinary / Dispensing11/1
Veterinary / Repeat Prescriptions11/1
Veterinary / Supplier Ordering11/1
Warehousing / Inventory Control11/1
Web Operations / Domain Management10/1
Work & Operations11/1
Workforce Scheduling10/1
Workplace / Payroll11/1

Head-to-head comparisons

Browse every run by Claude Haiku 5.5 →

From published single-model runs only (all settings grouped). How we score.