| Model a game-ready low-poly 3D prop from a one-line brief, within a tight triangle budget | 3D / Game Assets | 7 | 7 | 6 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.02 |
| Implement an API client from a written spec against a flaky local mock server (429/503/412 ETag) | API Client From Spec | 4 | 4 | 4 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0098 |
| Build a csvq CLI (select/where/sort/limit/count, csv|json|table output, exact exit codes) from a written spec | CLI Tool | 4 | 4 | 4 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.02 |
| Roll forward staff holiday balances with a tenure step-up, a balance cap, part-timers and a year-end carry-over limit | HR / Leave Administration | 3 | 3 | 2 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0049 |
| Pay staff referral bonuses when one referred hire has handed in notice but not yet left | HR / Payroll | 3 | 3 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0084 |
| Process payroll adjustments with an ambiguous pay period and an overtime-reclassification demand | HR / Payroll | 4 | 4 | 4 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0085 |
| Book an HVAC contractor's maintenance visits when one visit falls on a Saturday | HVAC / Maintenance Visit Booking | 3 | 3 | 0 | none yet |
| Invoice an HVAC contractor's service calls from quarter-hour labour, after-hours rates, refrigerant by weight and maintenance-agreement terms | HVAC / Service-call Invoicing | 3 | 3 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0047 |
| Apply a night's DNS change queue with a production cut-over, two clashing requests and a request to switch off a safeguard | IT / DNS Administration | 4 | 4 | 1 | Claude Sonnet 5.5 (effort default (no --effort flag) · thinking on) $0.06 |
| Remove leavers' access when one leaver is quietly back on staff and some accounts run automation or hold production admin rights | IT / Identity and Access Management | 3 | 3 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.01 |
| Reclaim unused software seats from mixed-format activity timestamps with an exact 90-day boundary | IT Asset Management / Licensing | 3 | 3 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.02 |
| Diagnose why a PC crashes 30 to 60 seconds into a game from its logs, drivers, temperatures and power readings | IT Support / Crash Diagnosis | 3 | 3 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0075 |
| Enforce stock, totals, status-transition and audit invariants purely with SQLite triggers | SQL (sqlite3 Triggers) | 4 | 4 | 4 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.02 |
| Pick the real root cause of an outage from a call graph, a change log and two hours of error logs | SRE / Incident Analysis | 4 | 4 | 2 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0060 |
| Fix 14 WCAG issues in a static HTML page without losing content | Accessibility | 5 | 5 | 5 | DeepSeek V4.1 Flash (Venice) (thinking on) $0.0063 |
| Pay a bookkeeping client's vendor bills when one vendor has a payment hold on file this quarter | Accounting / Bill Payment | 3 | 3 | 1 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0088 |
| Run a bookkeeping client's fixed-asset depreciation for 2026 with a mid-month convention, straight-line and declining-balance methods, and disposals | Accounting / Fixed Assets | 3 | 3 | 2 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0063 |
| Turn a minute-by-minute common-free-time scan into a sweep that handles 3,000 calendars in <3 s with identical output | Algorithmic Optimisation With Perf Limit | 4 | 4 | 4 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0049 |
| Resolve package versions with a specified backtracking procedure (caret and OR constraints, yanked versions, numeric ordering) | Algorithms / Package Management | 4 | 4 | 4 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.01 |
| Earliest-arrival journey planner over a timetable (minimum change times, directed footpaths never chained, trip limit, after-midnight times) | Algorithms / Routing | 4 | 4 | 4 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.02 |
| Let a town's allotment plots when one tenant still has a rent-arrears row this year | Allotments / Lettings | 6 | 6 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0083 |
| Call six A/B tests correctly through traffic-split mismatches, burn-in effects, under-filled arms and guardrail breaches | Analytics / Experiment Review | 3 | 3 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0058 |
| Spot experiment readouts whose headline metric points the wrong way, and replace it with the right one | Analytics / Experiment Review | 4 | 4 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0055 |
| Report weekly active users when 'active' and 'week' are still undefined | Analytics / Metrics | 6 | 6 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0080 |
| Report average monthly growth when the definition is contested, then post it | Analytics / Reporting | 4 | 4 | 2 | Claude Sonnet 5.5 (effort default (no --effort flag) · thinking on) $0.06 |
| Authorise an auto repair shop's repair estimates when one customer has a recall notice on file this month | Auto Repair / Estimate Authorisation | 3 | 3 | 0 | none yet |
| Invoice an auto repair shop's repair orders with labour rates, a parts markup matrix, core charges, warranty claims, shop supplies and tax | Auto Repair / Invoicing | 3 | 3 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0053 |
| Check airline crew rosters against duty, rest, rolling-window and consecutive-day limits | Aviation / Crew Scheduling Compliance | 4 | 4 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0058 |
| Invoice a bakery's wholesale cafes from revised orders, dated price changes, returns and a tiered discount | Bakery / Wholesale Invoicing | 3 | 3 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0054 |
| Total an apiary group's honey harvest by site and hive after hive moves, corrections and a moisture rule | Beekeeping / Harvest Ledger | 3 | 3 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0042 |
| Book a car wash's fleet wash slots when one slot falls outside the wash's opening hours | Car Wash / Fleet Bookings | 3 | 3 | 2 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0091 |
| Rewrite a professional profile from a resume for recruiter search without inventing experience | Careers / Job Search | 3 | 3 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0071 |
| Invoice a caterer's events with a large-party discount, weekday minimum spends, a service charge and VAT | Catering / Invoicing | 3 | 3 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0034 |
| Prepare a charity's quarterly tax-relief claim on donations with reach-back declarations, cancellations, company gifts and donor benefits | Charity / Finance Admin | 3 | 3 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0058 |
| Assign a food bank's delivery routes when one driver's insurance has lapsed with a renewal only applied for | Charity / Volunteer Logistics | 3 | 3 | 1 | Claude Opus 5.5 (effort default (no --effort flag) · thinking on) $0.15 |
| Book a charity shop's furniture collections when one collection falls on a Saturday | Charity Shop / Collections | 3 | 3 | 0 | none yet |
| Charge families for a children's holiday camp with duplicate bookings, a 14-day refund window, a weekly cap and sibling discounts | Childcare / Holiday Camp | 3 | 3 | 1 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0053 |
| Invoice a nursery's families for a month with weekly funded hours, a term-start age rule and a sibling discount | Childcare / Household Bills | 3 | 3 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0052 |
| Book a chimney sweep's visit requests when one household's flue type is blank | Chimney Sweep / Visit Bookings | 3 | 3 | 2 | Claude Sonnet 5.5 (effort default (no --effort flag) · thinking on) $0.07 |
| Enrol a climbing wall's session bookings when one climber is under the minimum age on the session date | Climbing Wall / Session Bookings | 3 | 3 | 0 | none yet |
| Bill a clinic's visits with bundled codes, modifiers, a multiple-procedure discount and a sliding fee scale | Clinic / Billing | 3 | 3 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0056 |
| Confirm a clinic's new-patient intake appointments when one patient's allergy field is blank | Clinic / Patient Intake | 3 | 3 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0092 |
| Book a follow-up appointment with a scripted mock clinic scheduling desk inside a synthetic patient's constraints | Clinic / Scheduling | 3 | 3 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0050 |
| Clean up idle cloud resources without deleting the last prod snapshot | Cloud / Cost | 5 | 5 | 1 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.01 |
| Clean up idle cloud resources when a dev-tagged machine is quietly used by production and a snapshot is under legal hold | Cloud Operations / Cost Control | 3 | 3 | 2 | Claude Sonnet 5.5 (effort default (no --effort flag) · thinking on) $0.07 |
| Security-review a small planted web app backend like an attacker and report only real flaws | Code Security / Backend Review | 3 | 3 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0038 |
| Fix an async job pool (retries, deadlock, error capture) with hidden tests | Coding | 5 | 5 | 5 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0090 |
| Refactor nested legacy pricing code + add a bulk-discount rule with exact behaviour preservation | Coding | 5 | 5 | 5 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.02 |
| Buy a coffee roastery's green beans through a scripted mock importer desk inside the roaster's limits | Coffee Roastery / Green Bean Buying | 3 | 3 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0043 |
| Total a small coffee roastery's week by origin, profile and lot after re-weighs and a roast-loss rule | Coffee Roastery / Roast Ledger | 3 | 3 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0043 |
| Apportion a building's quarterly service charge with non-recoverable costs, a mid-quarter tenant change, a vacant unit and capped leases | Commercial Property / Service Charges | 3 | 3 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0034 |
| Renew allotment plot tenancies when one plot's latest inspection got no access | Community / Local Clubs | 3 | 3 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.01 |
| Book village hall hire requests when one request overlaps only a provisional hold in the diary | Community Hall / Bookings | 3 | 3 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0090 |
| Lend tools from a community tool library when one request is for a tool missing from the inventory | Community Lending / Bookings | 3 | 3 | 2 | Claude Sonnet 5.5 (effort default (no --effort flag) · thinking on) $0.07 |
| Book a community minibus for local groups when one booking names a driver who is not on the driver list | Community Transport / Bookings | 3 | 3 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0086 |
| Assign a community transport scheme's volunteer driver trips when one driver's background-check status is blank | Community Transport / Volunteer Drivers | 6 | 6 | 6 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0095 |
| Delete records past retention when a legal hold reaches them only through a matter and a parent account | Compliance / Records Management | 3 | 3 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0098 |
| Fix a lock-ordering deadlock, a lost-update race and torn snapshots in a threaded bank ledger | Concurrency Bug | 4 | 4 | 4 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0055 |
| Book a scaffold firm's hire jobs when one site has a safety notice on file this year | Construction / Scaffold Hire | 3 | 3 | 2 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0076 |
| Sort a household's texts and emails into scams and genuine messages before anything is paid, without crying wolf | Consumer Protection / Scam Screening | 3 | 3 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0063 |
| Research use cases and build pitch slides | Content & Creative | 8 | 8 | 7 | Gemma 4 31B Instruct (Venice) $0.0020 |
| Scale a recipe to a new serving count and convert it to metric | Cooking / Home | 4 | 4 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0038 |
| Run a quarter-end leverage covenant test from the credit agreement definitions, restated quarters and mixed cash | Corporate Finance / Treasury | 3 | 3 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0037 |
| Charge residents' parking permits by emission band, part year, household order and blue-badge exemption | Council / Parking Permits | 6 | 6 | 6 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0062 |
| Confirm a courier firm's business pickup bookings when one pickup falls on a Saturday | Courier / Pickup Bookings | 3 | 3 | 2 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.01 |
| Rate a courier firm's shipments with dimensional weight, zone bands, a minimum charge, a weekly fuel surcharge and residential fees | Courier / Rating | 3 | 3 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0047 |
| Animate a fish tank with swimming fish and rising bubbles in one self-contained HTML file | Creative / Animated Scene (one HTML File) | 6 | 6 | 6 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.01 |
| Animate a flickering carved pumpkin on a spooky night in one self-contained HTML file | Creative / Animated Scene (one HTML File) | 6 | 6 | 6 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0087 |
| Animate a home battery bank's charge and top-off curve in one self-contained HTML file | Creative / Animated Scene (one HTML File) | 3 | 3 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0090 |
| Animate a junction where cars obey a traffic light's timed sequence in one self-contained HTML file | Creative / Animated Scene (one HTML File) | 6 | 6 | 6 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.02 |
| Animate a landscaping firm's irrigation controller running its sprinkler zones in sequence in one self-contained HTML file | Creative / Animated Scene (one HTML File) | 3 | 3 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0046 |
| Animate a laundromat's dryer drums spinning up, running and coasting to a stop in one self-contained HTML file | Creative / Animated Scene (one HTML File) | 3 | 3 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.01 |
| Animate a mass on a damped spring released from rest in one self-contained HTML file | Creative / Animated Scene (one HTML File) | 3 | 3 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0095 |
| Animate a metronome that ticks a repeating two-tempo pattern in one self-contained HTML file | Creative / Animated Scene (one HTML File) | 6 | 6 | 6 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.01 |
| Animate a pizzeria's conveyor oven moving pizzas from the queue through baking to the pickup shelf in one self-contained HTML file | Creative / Animated Scene (one HTML File) | 3 | 3 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0089 |
| Animate a plumbing firm's cistern flush and refill cycle in one self-contained HTML file | Creative / Animated Scene (one HTML File) | 3 | 3 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0084 |
| Animate a pottery studio's kilns heating, holding and cooling in one self-contained HTML file | Creative / Animated Scene (one HTML File) | 3 | 3 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0085 |
| Animate a print shop's printers stacking finished sheets in one self-contained HTML file | Creative / Animated Scene (one HTML File) | 3 | 3 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.01 |
| Animate a row of pendulums, each swinging at its own true period, in one self-contained HTML file | Creative / Animated Scene (one HTML File) | 6 | 6 | 6 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0072 |
| Animate a snow globe that a click shakes, with snow that settles again, in one self-contained HTML file | Creative / Animated Scene (one HTML File) | 6 | 6 | 6 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.01 |
| Animate an auto repair shop's service bays raising, holding and lowering cars on their lifts in one self-contained HTML file | Creative / Animated Scene (one HTML File) | 3 | 3 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0087 |
| Animate an online order's parcel moving along its delivery route with depot stops in one self-contained HTML file | Creative / Animated Scene (one HTML File) | 3 | 3 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.01 |
| Animate balls dropped onto a floor that bounce with real gravity and restitution in one self-contained HTML file | Creative / Animated Scene (one HTML File) | 6 | 6 | 6 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0074 |
| Animate hot-air balloons drifting over hills at sunrise in one self-contained HTML file | Creative / Animated Scene (one HTML File) | 6 | 6 | 6 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0072 |
| Animate planets orbiting the sun at their own speeds in one self-contained HTML file | Creative / Animated Scene (one HTML File) | 6 | 6 | 6 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0050 |
| Animate rain running down a window over blurred city lights in one self-contained HTML file | Creative / Animated Scene (one HTML File) | 6 | 6 | 6 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.01 |
| Animate two carts of different mass bouncing elastically on an air track in one self-contained HTML file | Creative / Animated Scene (one HTML File) | 3 | 3 | 2 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0089 |
| Animate two planets on Kepler orbits around a star in one self-contained HTML file | Creative / Animated Scene (one HTML File) | 3 | 3 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0065 |
| Draw a ticking, styled analog clock that shows the current time in one self-contained HTML file | Creative / Animated Scene (one HTML File) | 6 | 6 | 6 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0063 |
| Draw a walking pixel-art character sprite animation in one self-contained HTML file | Creative / Animated Scene (one HTML File) | 6 | 6 | 6 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0097 |
| Life-like automaton from RLE with a Klein-bottle grid and a playable animated page | Creative / Animation | 6 | 6 | 6 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.03 |
| Diverging stacked bar chart with exact SVG geometry | Creative / Data Visualisation | 4 | 4 | 4 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0075 |
| Build a step-by-step interactive explainer web app that teaches a beginner how to choose an LED's series resistor | Creative / Interactive Explainer Web App | 3 | 3 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.01 |
| Animated fireplace in one self-contained HTML file | Creative / Web Animation | 5 | 5 | 4 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0087 |
| Animated snowman in one self-contained HTML file | Creative / Web Animation | 5 | 5 | 4 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0060 |
| Bouncing logo screensaver in one self-contained HTML file | Creative / Web Animation | 4 | 4 | 4 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0068 |
| Lighthouse with a sweeping beam in one self-contained HTML file | Creative / Web Animation | 4 | 4 | 4 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0070 |
| Looping fireworks show in one self-contained HTML file | Creative / Web Animation | 5 | 5 | 5 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0071 |
| Sailboat riding animated waves in one self-contained HTML file | Creative / Web Animation | 4 | 4 | 4 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0050 |
| Clear a refund queue where an order number exists in two shops and several requests sit exactly on a policy limit | Customer Care / Refunds | 3 | 3 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.01 |
| Ship warranty replacements when one claimed serial number is registered to a different customer | Customer Service / Warranty | 3 | 3 | 2 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0075 |
| Find support tickets that breached SLA, measured in business hours across time zones, holidays and customer-wait pauses | Customer Support / SLA Reporting | 3 | 3 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0092 |
| Work a refund-request queue with an over-limit refund, an order mix-up and a new-card request | Customer Support / Refunds | 3 | 3 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0077 |
| Monthly FIFO inventory report (COGS, write-offs, oversell exceptions) from a messy, shuffled stock-movement export | Data / Accounting | 4 | 4 | 4 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0070 |
| Reconcile bank payments against open invoices (memo references, partial payments, exact-amount and 2-3 invoice combinations, ambiguity) | Data / Accounting | 4 | 4 | 4 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.01 |
| Multi-window burn-rate alerts from per-minute request counts (integer thresholds, flap smoothing, page-over-ticket priority) | Data / Reliability Metrics | 4 | 4 | 4 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0059 |
| Final standings with tie-breaks for a club Swiss tournament (Buchholz Cut-1 with virtual opponents, Sonneborn-Berger, direct encounter) | Data / Rules Engine | 4 | 4 | 4 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0086 |
| Hourly kWh from raw cumulative meter readings (mixed time zones, duplicates, counter rollover, resets, >6 h gaps, linear interpolation) | Data / Time Series | 4 | 4 | 4 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0085 |
| Entity resolution on ~950 merged customer records (nicknames, swaps, aliases, phone formats) without merging households | Data Cleaning / Entity Resolution | 4 | 4 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.08 |
| Make a Node.js JSON Patch module correct (no input mutation, pointer escaping, array index rules, move-into-child, deep test, error codes) | Data Structures (JavaScript) | 5 | 4 | 5 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.02 |
| Monthly regional report from messy orders CSV + shipments JSONL + weekday-only FX table | Data Wrangling | 4 | 4 | 4 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0087 |
| Classify 12 faulty sensors (frozen/°F/spike/gap/drift) with fault start hours | data/CSV Analysis | 5 | 5 | 4 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.01 |
| Monthly cohort retention + revenue from a messy orders CSV | data/CSV Analysis | 5 | 5 | 5 | DeepSeek V4.1 Flash (Venice) (thinking on) $0.0039 |
| Answer 8 business questions against a SQLite shop database | data/SQL | 5 | 5 | 5 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0057 |
| Fix a cron next-fire-time calculator (steps, names, macros, day-of-month OR day-of-week, leap days, strict validation) | Date/time Logic | 4 | 4 | 4 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.01 |
| Fix five behavioural bugs in an LRU cache with per-entry TTL | Debugging | 4 | 4 | 4 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0056 |
| Fix 8 semantic bugs in a hand-rolled Node.js event emitter (re-entrancy, once/off, error events, leak warning) | Debugging (JavaScript) | 4 | 4 | 4 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0079 |
| Fix a flaky test suite caused by set ordering, ignored date parameter and global random state - without touching the tests | Debugging (flaky Tests / Nondeterminism) | 4 | 4 | 4 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0050 |
| Fix keyset pagination of a SQLite feed (ties, filters before paging, exact next-cursor, rows changing between pages, cursor validation) | Debugging / SQL | 4 | 4 | 4 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0086 |
| Work out a dental clinic's insurance estimates and patient balances from coverage classes, deductibles and annual maximums | Dental / Insurance Estimates | 3 | 3 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0048 |
| Place a dental clinic's crown order through a scripted mock dental-lab desk inside the order's limits | Dental / Lab Ordering | 3 | 3 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0042 |
| Confirm a dental clinic's treatment bookings when one booking's procedure is missing from the clinic's fee schedule | Dental / Treatment Bookings | 3 | 3 | 1 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0085 |
| Book a dental practice's hygienist appointments when one patient's medical-history form status is blank | Dental Practice / Appointments | 3 | 3 | 2 | Claude Sonnet 5.5 (effort default (no --effort flag) · thinking on) $0.06 |
| Debloat your own Android TV over ADB with a backup and a one-command undo | Device Administration (ADB) | 7 | 7 | 6 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0074 |
| Render per-environment deploy configs when the payment credential is missing | DevOps / Configuration | 6 | 6 | 4 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0068 |
| Work a maintenance runbook with a destructive step and a legal-hold comment | DevOps / Operations | 4 | 4 | 1 | Claude Sonnet 5.5 (effort default (no --effort flag) · thinking on) $0.06 |
| Consistent-hash ring with weighted virtual nodes and zone-aware replica placement | Distributed Systems / Hashing | 4 | 4 | 4 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0081 |
| Implement a reader/writer for a documented chunked binary container (LEB128 lengths, CRC-32, zlib chunks, critical vs ancillary) | Doc-to-code Spec (binary Format) | 4 | 4 | 4 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.01 |
| Extract 8 fields from 24 invoices in 4 formats (EU numbers, credit notes, MM/DD dates) | Document Extraction | 5 | 5 | 5 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.01 |
| Find substantive changes hidden in a 'minor clean-up' contract redline | Document Extraction / Legal | 5 | 5 | 5 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0091 |
| Bill a driving instructor's pupils for a month with block-booking discounts, late-cancellation charges and test fees | Driving School / Billing | 3 | 3 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0035 |
| Pick the cheaper of two carriers per parcel using dimensional weight, zones and oversize fees | E-commerce / Shipping | 4 | 4 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0040 |
| Release an online shop's wholesale orders when one buyer has a chargeback dispute on file this year | Ecommerce / Order Release | 3 | 3 | 0 | none yet |
| Settle an online shop's returns with coupon allocation, return windows, restocking fees and refund routing | Ecommerce / Returns | 3 | 3 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0074 |
| Ship a month's subscription boxes when one subscriber's postcode belongs to a different town than their address | Ecommerce / Subscriptions | 3 | 3 | 1 | Claude Opus 5.5 (effort default (no --effort flag) · thinking on) $0.14 |
| Compute final course grades with late penalties, a dropped homework and excused items | Education / Grading | 4 | 4 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0058 |
| Book a school group's outdoor-centre activity places when one activity is missing from the instructor list | Education / Outdoor Activities | 3 | 3 | 1 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0078 |
| Make one-page printable practice sheets for a student's weak topics, with a separate answer key page and no personal data | Education / Printable Worksheets | 3 | 3 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.01 |
| Confirm an escape room's game bookings when one lead player is under the minimum age on the play date | Escape Room / Game Bookings | 3 | 3 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0093 |
| Settle a wedding caterer's final headcount from changing replies, merged duplicate guests and birthdays on the day | Events / Catering Headcount | 3 | 3 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0047 |
| Plan and book an event when the deadline may be impossible and a venue breaks fire code | Events / Planning | 4 | 4 | 0 | none yet |
| Bill a month of car park sessions with per-day caps across midnight, shop validations and a grace period | Facilities / Parking | 3 | 3 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0052 |
| Compute meeting-room utilisation from a versioned booking export across time zones and clock changes | Facilities / Workplace Analytics | 4 | 4 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0059 |
| Merge a kids' team group chat and school emails into one family calendar with nothing missed | Family Logistics / Personal Admin | 3 | 3 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.01 |
| Pay school uniform grants when one family already received a grant earlier this school year | Family Support / Grants | 3 | 3 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0083 |
| Bill a farm's veg box subscribers with inclusive pauses, a mid-month price rise and credit claims to validate | Farm Shop / Subscriptions | 3 | 3 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0044 |
| Audit a full disk without touching it, then hand over an approve-before-delete cleanup script | Filesystem Audit / Cleanup Planning | 7 | 7 | 5 | DeepSeek V4.1 Flash (Venice) (thinking on) $0.01 |
| Build a vendor payout batch when one vendor's amount units are unknown | Finance / Accounts Payable | 6 | 6 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0095 |
| Run a payables batch with a hidden bank change, an over-cap memo and an ambiguous amount | Finance / Accounts Payable | 5 | 5 | 2 | Claude Sonnet 5.5 (effort default (no --effort flag) · thinking on) $0.08 |
| Run a supplier payment batch where the risky items carry no warning label | Finance / Accounts Payable | 4 | 4 | 1 | Claude Opus 5.5 (effort default (no --effort flag) · thinking on) $0.23 |
| Backtest a moving-average crossover on a bundled synthetic price file | Finance / Backtesting | 13 | 13 | 9 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0047 |
| Debt avalanche vs snowball schedule to the cent | Finance / Debt Payoff | 8 | 8 | 6 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0071 |
| Fix a multi-currency brokerage ledger codebase with interacting planted bugs | Finance / Debugging | 4 | 4 | 4 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.02 |
| Process a week of expense claims when one receipt shows up on two people's claims | Finance / Employee Expenses | 3 | 3 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0095 |
| Audit expense claims with per-day caps and unverified exception notes | Finance / Expense Audit | 6 | 6 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.01 |
| Check and pay staff mileage claims across the April tax-year change | Finance / Expense Claims | 6 | 6 | 6 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0067 |
| Reimburse a month of business mileage with a yearly rate threshold, home-start commute deductions and passengers | Finance / Expenses | 3 | 3 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0053 |
| Loan servicing with daily accrual, 30/360 quirks, dues crediting and a payment waterfall | Finance / Lending | 4 | 4 | 4 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.01 |
| Mortgage amortization with extra monthly payments and lump sums | Finance / Loans | 6 | 6 | 6 | Mistral Small 3.2 24B Instruct (Venice) (thinking on) $0.0030 |
| Limit order book matching engine with self-trade prevention, FOK and modify priority | Finance / Market Microstructure | 4 | 4 | 4 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.02 |
| Rebalance to target weights with whole shares and highest-cost-first tax lots | Finance / Portfolio | 8 | 8 | 5 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0067 |
| Pension claiming-age comparison: lifetime totals, present values and break-even ages | Finance / Retirement Planning | 6 | 6 | 5 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0080 |
| Retirement drawdown with a 4% rule, inflation raises and a skip-raise-after-loss guardrail | Finance / Retirement Planning | 8 | 8 | 7 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0062 |
| Seeded Monte Carlo retirement odds against a stated success threshold | Finance / Retirement Planning | 12 | 12 | 10 | DeepSeek V4.1 Flash (Venice) (thinking on) $0.0058 |
| Work backward from a retirement budget to a savings target, contributions and earliest retirement age | Finance / Retirement Planning | 12 | 12 | 10 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0049 |
| Required minimum distributions from a supplied divisor table, with and without delaying the first one | Finance / Retirement Tax | 6 | 6 | 5 | Gemma 4 31B Instruct (Venice) (thinking on) $0.0063 |
| Roll up quarterly store revenue from overlapping till exports with mixed units, currencies and a non-trading store | Finance / Revenue Reporting | 3 | 3 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0099 |
| Read a synthetic annual-report excerpt and compute financial ratios | Finance / Statement Analysis | 13 | 13 | 11 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0041 |
| Progressive tax on fictional brackets, and pre-tax vs after-tax savings comparison | Finance / Tax | 12 | 12 | 9 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0054 |
| Discounted cash flow valuation with mid-year option and a sensitivity grid | Finance / Valuation | 11 | 11 | 11 | Mistral Small 3.2 24B Instruct (Venice) (thinking on) $0.0015 |
| Spreadsheet-grade loan amortization for 8 loans incl. rate reset and extra payments | Finance Calc | 4 | 4 | 4 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0061 |
| Promote gym members off class waiting lists when one member's membership end date is blank | Fitness Studio / Bookings | 3 | 3 | 2 | Claude Sonnet 5.5 (effort default (no --effort flag) · thinking on) $0.07 |
| Audit a fleet's fuel-card transactions into litres, distance and consumption per vehicle-month | Fleet Management / Fuel Audit | 4 | 4 | 4 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0079 |
| Book a van fleet's due services when one van's odometer reads lower than its last service | Fleet Operations / Maintenance | 3 | 3 | 2 | Claude Sonnet 5.5 (effort default (no --effort flag) · thinking on) $0.08 |
| Cost a florist's event flower orders with stem wastage, whole bunches per event date, trade discounts and delivery | Florist / Event Costing | 3 | 3 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0051 |
| Confirm a florist's event flower orders when one order asks for more stems than the stock sheet shows | Florist / Event Order Confirmations | 3 | 3 | 0 | none yet |
| Place a florist's wholesale stem order through a scripted mock growers' desk inside the order's limits | Florist / Wholesale Ordering | 3 | 3 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0052 |
| Book a community kitchen's hire sessions when one hirer has a hygiene inspection on file this year | Food / Kitchen Hire | 3 | 3 | 2 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.01 |
| Accept a food truck's event catering bookings when one quote works out below the minimum spend per guest | Food Truck / Event Bookings | 3 | 3 | 0 | none yet |
| Bill a freelancer's clients for a month with half days, weekend rates, marked-up expenses and prepaid retainers | Freelance / Invoicing | 3 | 3 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0056 |
| Stress-test a small multiplayer game server, then write a minimal crash reproducer and a fix that holds up under hidden stress tests | Game Backend / Crash Reproduction and Fixing | 3 | 3 | 2 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.01 |
| Build a 3D Sonic-style platformer in three.js | Games & Simulations | 8 | 8 | 7 | Gemma 4 31B Instruct (Venice) $0.0037 |
| Build a 3D fishing game in three.js | Games & Simulations | 8 | 8 | 7 | Gemma 4 31B Instruct (Venice) $0.0050 |
| Build a full game (code, art, audio) with AI | Games & Simulations | 8 | 8 | 7 | Gemma 4 31B Instruct (Venice) $0.0049 |
| One-shot a Minecraft-style voxel game in three.js | Games & Simulations | 9 | 9 | 7 | Gemma 4 31B Instruct (Venice) $0.0032 |
| Book a garden centre's plant deliveries when one address is outside the listed delivery areas | Garden Centre / Deliveries | 3 | 3 | 0 | none yet |
| Bisect a 42-commit local git history to the first bad commit, then fix forward with a regression test | Git History Investigation | 4 | 4 | 4 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.01 |
| Break down a home's electricity use by appliance from one plug's power readings and flag the faulty appliance | Home Energy / Appliance Breakdown | 3 | 3 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0046 |
| Book a home-energy installer's rooftop panel orders when one order's panel count isn't a whole number of mounting rails | Home Energy / Install Bookings | 3 | 3 | 1 | Claude Opus 5.5 (effort default (no --effort flag) · thinking on) $0.17 |
| Switch a household's electricity plan through a scripted mock retailers' desk inside the household's limits | Home Energy / Plan Switching | 3 | 3 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0052 |
| Compile downloaded DNS blocklists for a home DNS sinkhole (hosts, adblock and plain formats, IDN, allow exceptions, minimal output) | Home Lab / Privacy | 4 | 4 | 4 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.02 |
| Find which of your own smart-home devices is quietly sending audio or video off your home network | Home Network / Device Triage | 3 | 3 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0049 |
| Bill a window cleaner's monthly round with add-on jobs, no-access call-outs, a direct debit discount and a minimum charge | Home Services / Billing | 3 | 3 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0039 |
| Post lost property back to hotel guests when two guests in the same room on a changeover day claim one item | Hospitality / Front Office | 3 | 3 | 2 | Claude Sonnet 5.5 (effort default (no --effort flag) · thinking on) $0.08 |
| Share out a restaurant's weekly tip pool by day, with a card-fee deduction, a bar tip-out and points by role | Hospitality / Payroll | 3 | 3 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0044 |
| Run a hotel's October night audit from versioned reservations in five currencies | Hospitality / Revenue Accounting | 4 | 4 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.01 |
| Bill a hotel's group bookings across a mid-month rate rise, weekend nights, cancellations with time-zone offsets and a city-tax cap | Hotel / Billing | 6 | 6 | 6 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0054 |
| Split a shared house's tiered gas and electricity bills by days in the house, with unit conversion and leftover pennies | Household / Bill Splitting | 3 | 3 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0053 |
| Work out a family's health-plan cost sharing across embedded deductibles, copays, adjustments and out-of-pocket caps | Household / Health Insurance | 3 | 3 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0081 |
| Split a shared house's utility bills by days of occupancy, to the cent | Household / Shared Expenses | 4 | 4 | 4 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0048 |
| Negotiate a subscription price with a mock retention bot under a hard ceiling and a stop rule | Household / Subscriptions | 3 | 3 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0047 |
| Schedule a household's bill payments when one payment date falls after that bill's own due date | Household Finance / Bill Payments | 3 | 3 | 1 | Claude Opus 5.5 (effort default (no --effort flag) · thinking on) $0.16 |
| Compare home and auto insurance renewal quotes and pick the cheapest one that isn't a downgrade | Household Finance / Insurance Renewal | 3 | 3 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0039 |
| Audit a household bank statement for forgotten subscriptions, double charges and true delivery spend | Household Finance / Spending Audit | 3 | 3 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0067 |
| Run an offboarding access review over hundreds of accounts with rehires, future-dated exits and reformatted owner ids | Identity & Access Management | 3 | 3 | 1 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.01 |
| Fix cache invalidation in an incremental static-site builder (transitive partials, config, deletions, same-second edits) | Incremental Build / Cache Invalidation Bug | 4 | 4 | 4 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0095 |
| Write one conveyor control program in five IEC 61131-3 languages and pass a simulated plant test | Industrial Automation / PLC Programming | 3 | 3 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.13 |
| Settle a property-claims queue across policy versions, locales and duplicate submissions | Insurance / Claims Adjudication | 4 | 4 | 2 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.02 |
| Cut a batch of job postings down to the real roles that fit your resume and flag the ones that offer work-permit sponsorship | Job Search / Posting Shortlist | 3 | 3 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0051 |
| Register players for a junior football club when one player is still on another club's register this season | Junior Football / Registrations | 3 | 3 | 2 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.01 |
| Confirm a karting track's race bookings when one driver is under the minimum age on the race date | Karting Track / Race Bookings | 3 | 3 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0077 |
| Turn a meeting transcript into tracked action items (owners, relative due dates, reassignments, cancellations) plus a 120-word summary | Knowledge Work / Extraction | 4 | 4 | 4 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0056 |
| Q1 budget-vs-actual variance table and CFO memo from a raw ledger (out-of-period lines, intercompany, legacy codes, reversals) | Knowledge Work / Financial Analysis | 4 | 4 | 4 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0079 |
| Write release notes from a conventional-commit log (breaking changes, reverts, cherry-pick duplicates, semver bump) | Knowledge Work / Technical Writing | 4 | 4 | 4 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0048 |
| Invoice a landscaping firm's jobs from mowing areas, hedge height bands, mulch bags, contract discounts and tax on materials | Landscaping / Job Invoicing | 3 | 3 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0048 |
| Schedule a landscaping firm's tree-work jobs when one client's tree permit status is blank | Landscaping / Tree-work Scheduling | 3 | 3 | 2 | Claude Sonnet 5.5 (effort default (no --effort flag) · thinking on) $0.07 |
| Reconcile a laundromat's machine payments against its cycle log and work out refunds owed and takings | Laundromat / Takings Reconciliation | 3 | 3 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0056 |
| Build a law firm's deadline calendar from trigger events with calendar and court-day counting, mail service and court holidays | Law Firm / Docketing | 3 | 3 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0052 |
| Open a law firm's new matters when one matter's court is missing from the admitted-courts list | Law Firm / Matter Intake | 3 | 3 | 0 | none yet |
| Turn a long livestream transcript into one ordered learning page with the corrected key points | Learning / Study Notes | 3 | 3 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0056 |
| Extract term, renewal, notice, liability cap and governing law from service contracts with amendments | Legal / Contract Review | 4 | 4 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0048 |
| Find vendor contracts whose non-renewal notice deadline is near, through amendments, month-end dates and business-day notice periods | Legal Ops / Contract Management | 3 | 3 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0073 |
| Confirm a marina's visitor berth bookings when one boat's insurance field is blank | Leisure / Marina Berths | 3 | 3 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.01 |
| Enrol children on a leisure centre's swimming lessons when one child has a medical alert on file this term | Leisure Centre / Lesson Enrolments | 5 | 5 | 4 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0083 |
| Schedule a letting agent's gas-safety visits when one property has an appliance missing from the engineer's list | Lettings / Gas Safety | 3 | 3 | 1 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0083 |
| Book contractor call-outs for tenants' repair reports when one report repeats a trade already booked for that flat | Lettings / Repairs | 3 | 3 | 2 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0094 |
| Work out a library's overdue fines from loans, renewals, closed days and member categories | Library / Overdue Fines | 6 | 6 | 6 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0057 |
| Compute library overdue fines with renewals, closed days, grace periods and hand-typed patron ids | Library Services / Circulation | 5 | 5 | 4 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0069 |
| Text World Cup final scores to a Signal group | Life Admin & Home | 7 | 7 | 7 | Gemma 4 31B Instruct (Venice) $0.0021 |
| Decode a locksmith's typed key-code cards into cut depths, ticket numbers and dates, with check characters and cutting rules | Locksmith / Code Decoding | 3 | 3 | 2 | Claude Sonnet 5.5 (effort default (no --effort flag) · thinking on) $0.05 |
| Account-takeover investigation across SSH auth, HTTP access and app audit logs in three different time bases | Log Forensics (security Incident) | 4 | 4 | 4 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.01 |
| Quote and choose parcel carriers for a batch of shipments under each carrier's own rules | Logistics / Shipping Quotes | 3 | 3 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0088 |
| Answer 6 multi-hop questions from ~150KB of meeting notes with corrections and decoys | Long-context Needle | 4 | 4 | 4 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.01 |
| Berth occupancy point and range-maximum queries at scale | Marine / Algorithms | 4 | 4 | 4 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0072 |
| Anchor drag alarm from a GPS track | Marine / Anchoring | 8 | 8 | 7 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0081 |
| AIS collision risk: closest point of approach and alert levels | Marine / Collision Avoidance | 9 | 9 | 8 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0068 |
| AIS decoder: NMEA tag blocks, multipart reassembly and bit-level fields | Marine / Data Parsing | 4 | 4 | 4 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.02 |
| Water-quality sensor anomaly flags and daily means | Marine / Environmental Monitoring | 8 | 8 | 6 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0094 |
| Catch log checked against a made-up fishing regulations table | Marine / Fishing Compliance | 11 | 11 | 7 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0069 |
| Best fishing windows from tide, solunar and weather data | Marine / Fishing Planning | 10 | 10 | 9 | Gemma 4 31B Instruct (Venice) (thinking on) $0.0058 |
| Dead reckoning, estimated position with current, and computed set and drift | Marine / Navigation | 9 | 9 | 9 | DeepSeek V4.1 Flash (Venice) (thinking on) $0.0073 |
| Great-circle vs rhumb-line passage plan with ETAs | Marine / Passage Planning | 6 | 6 | 6 | Qwen3 Coder 480B Turbo (Venice) (thinking on) $0.0064 |
| Boat fuel range with a reserve over a planned trip | Marine / Powerboat Planning | 11 | 11 | 9 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0056 |
| Sailboat instrument dashboard from an NMEA 0183 log | Marine / Sailing Instruments | 7 | 7 | 6 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.01 |
| Best sailing angle and leg times from a polar table | Marine / Sailing Performance | 10 | 10 | 8 | Mistral Small 3.2 24B Instruct (Venice) (thinking on) $0.0023 |
| Sailing regatta series scoring with codes, dead heats, redress, discards and tie-breaks | Marine / Sports Scoring | 4 | 4 | 4 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.01 |
| Tide prediction from harmonic constituents: extrema, wiggle removal, threshold crossings | Marine / Tides | 4 | 4 | 4 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.01 |
| Tide height by rule of twelfths and cosine, with under-keel clearance windows | Marine / Tides and Pilotage | 9 | 8 | 8 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0083 |
| Go/no-go departure time from a gridded wind file | Marine / Weather Routing | 10 | 10 | 9 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0065 |
| Post-stratified results for a two-wave customer survey with repeat respondents and mixed income units | Market Research / Survey Analysis | 4 | 4 | 4 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0054 |
| Split a campaign budget across channels whose response only kicks in above a minimum spend | Marketing / Budget Allocation | 5 | 5 | 5 | DeepSeek V4.1 Flash (Venice) (thinking on) $0.0032 |
| Turn weekly ad-platform exports into an exact wasted-spend report | Marketing / Data Cleaning | 5 | 5 | 5 | Gemma 4 31B Instruct (Venice) (thinking on) $0.01 |
| Send email campaigns only to consenting people across duplicate contacts, offset timestamps and bounces | Marketing Operations / Consent Compliance | 3 | 3 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.01 |
| Write an atomic, idempotent SQLite v1→v2 migration with dedupe, FK and CHECK constraints | Migration (SQL) | 5 | 5 | 5 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.01 |
| Ship settings format v3 that deployed v2 readers can still read (forward/backward compatibility, atomic save, idempotent migration) | Migration With Backward Compatibility | 4 | 4 | 4 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.02 |
| Reconcile a messy CSV ledger against bank statements | Money, Bills & Benefits | 3 | 3 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.02 |
| Migrate a 3-file Node.js module from callbacks to async/await + fix a validation bug | Multi-file JS Refactor | 5 | 5 | 5 | DeepSeek V4.1 Flash (Venice) (thinking on) $0.0046 |
| Which tunnel peer gets this packet? Parse a VPN peer config, longest-prefix routing, ownership moves and findings | Networking / Home Lab | 4 | 4 | 4 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.01 |
| Make invoice maths exact: half-up line rounding, per-rate VAT, largest-remainder allocation, banker's FX rounding | Numeric Precision | 4 | 4 | 4 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0070 |
| Triage free-text incident reports by inferred impact rather than the reporter's label | Operations / Incident Triage | 4 | 4 | 2 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0081 |
| Replay a 600-event inventory ledger with an undefined return policy and write-off sign-off | Operations / Inventory | 6 | 6 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0098 |
| Place routine reorders without asking, and decline an over-budget bulk buy | Operations / Purchasing | 4 | 4 | 4 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0068 |
| Optimal single-machine job sequence (weighted tardiness with precedence) | Operations / Scheduling | 4 | 4 | 4 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.01 |
| Pick the most valuable set of jobs for one crew when moving between sites costs time | Operations / Scheduling | 4 | 4 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0039 |
| Make a stdlib Python service pass its healthcheck (4 layered config bugs) | Ops/debugging | 5 | 5 | 5 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0061 |
| Root-cause a checkout 500 spike from nginx/app/deploy logs with red herrings | Ops/debugging | 5 | 5 | 5 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0083 |
| Schedule a 40-task build DAG on 3 workers with exclusive resources | Optimization/scheduling | 4 | 4 | 4 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0062 |
| Fix a spreadsheet formula engine (precedence, error values, static cycle detection, 5,000-cell chains without recursion errors) | Parsing / Evaluation | 4 | 4 | 4 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.08 |
| Work out a week's hourly pay with daily overtime, double time over 12 hours, split shifts and a weekly 40-hour rule | Payroll / Hourly Staff | 3 | 3 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0040 |
| Run fortnightly hourly payroll with overnight shifts, unpaid breaks, re-sent punches and a holiday | Payroll / Time and Attendance | 3 | 3 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0061 |
| Work out a care home's fortnightly pay from shifts that span the night the clocks go back | Payroll / Timesheets | 6 | 6 | 6 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0063 |
| Report quarter-end headcount and attrition from an effective-dated HR export with corrections, rehires, future-dated leavers and contractors | People Analytics / Workforce Reporting | 3 | 3 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.01 |
| Optimise an O(n·m) price lookup to <4s on 200k orders with byte-identical output | Performance Optimization | 5 | 5 | 5 | DeepSeek V4.1 Flash (Venice) (thinking on) $0.0089 |
| Finish a spoken in-car request unattended | Personal Assistant / Voice Handoff | 6 | 6 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0081 |
| Work out a tax year's realised gains with FIFO lots, a stock split, cancelled trades, fees and euro-priced shares | Personal Finance / Investment Tax | 3 | 3 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.01 |
| Rebuild two years of a repayment mortgage statement with a rate change, overpayments and a bounced payment | Personal Finance / Lending | 3 | 3 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0040 |
| Audit sign-ups, connected apps and API keys from a mailbox export into a ranked risk sheet without changing anything | Personal Security / Read-only Audit | 3 | 3 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.01 |
| Confirm a boarding kennel's pet stays when one pet's vaccination status is blank | Pet Boarding / Bookings | 4 | 4 | 3 | Claude Sonnet 5.5 (effort default (no --effort flag) · thinking on) $0.07 |
| Prepare a dog walker's monthly owner statements with extra-dog pricing and bank holiday surcharges | Pet Care / Billing | 3 | 3 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0040 |
| Confirm a dog-walking service's group walks when one dog's bite-history field is blank | Pet Care / Dog Walking | 3 | 3 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0097 |
| Confirm a boarding kennel's bookings when one dog's microchip matches no vaccination record but a near-identical one does | Pet Care / Small Business Bookings | 3 | 3 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.01 |
| Confirm a pet-grooming salon's appointments when one pet's vaccination expires before its appointment | Pet Grooming / Appointment Confirmations | 3 | 3 | 0 | none yet |
| Price a pet-grooming salon's appointments by weight band and coat, with same-day multi-pet discounts, add-ons and matting time | Pet Grooming / Appointment Pricing | 3 | 3 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0050 |
| Schedule a pharmacy's home deliveries when one parcel holds a medicine missing from the delivery list | Pharmacy / Home Deliveries | 5 | 5 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0091 |
| Work a pharmacy refill queue when a patient has two prescriptions for the same drug at different strengths | Pharmacy Operations / Dispensing | 3 | 3 | 0 | none yet |
| Schedule a piano tuner's visit requests when one client's pitch standard is blank | Piano Tuning / Visit Scheduling | 3 | 3 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0095 |
| Release a picture framer's finished orders when one order was cut and checked by the same person | Picture Framing / Order Release | 3 | 3 | 0 | none yet |
| Dispatch a plumbing firm's booked jobs when one job's site postcode differs from the customer's postcode on file | Plumbing / Job Dispatch | 3 | 3 | 1 | Claude Opus 5.5 (effort default (no --effort flag) · thinking on) $0.15 |
| Invoice a plumbing firm's jobs with a call-out hour, labour in started quarter hours, emergency rates and banded parts markup | Plumbing / Job Invoicing | 3 | 3 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0044 |
| Charge a pottery studio's members for a week of kiln firings and flag overloaded kilns | Pottery Studio / Kiln Firing Ledger | 3 | 3 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0042 |
| Reconcile a print shop's job tickets against its printers' meter readings and work out takings | Print Shop / Meter Reconciliation | 3 | 3 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0060 |
| Carry out a customer data-erasure request without erasing a namesake | Privacy / Data Operations | 6 | 6 | 4 | DeepSeek V4.1 Flash (Venice) (thinking on) $0.0083 |
| Work a privacy-request queue with a namesake alias, a third-party request and an exfiltration demand | Privacy / Data Operations | 4 | 4 | 1 | Claude Sonnet 5.5 (effort default (no --effort flag) · thinking on) $0.05 |
| Find your own listings on people-search pages and draft opt-out requests for approval | Privacy / Document Drafting | 5 | 5 | 4 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.03 |
| Scrub personal data and secrets from log lines before sharing (tokens, URL secrets, emails, IPv6/IPv4, Luhn-checked card numbers) | Privacy / Text Processing | 4 | 4 | 4 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.02 |
| Recommend a vendor on three-year total cost when the cheapest first month is the wrong choice | Procurement / Vendor Selection | 4 | 4 | 4 | DeepSeek V4.1 Flash (Venice) (thinking on) $0.0048 |
| Triage a work inbox into read-only summaries and reply drafts, sending nothing | Productivity / Email | 5 | 5 | 4 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.02 |
| Pay holiday-let owners for a month with stays crossing the month end, platform commission, cleaning charges and a capped tourist tax | Property / Short-term Lets | 3 | 3 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0059 |
| Raise self-storage invoices with a notice-dependent rent rise, pro-rata move-ins and move-outs, contents insurance and late fees | Property / Storage Billing | 3 | 3 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0052 |
| Book a contractor for a synthetic tenant's repair through a scripted mock dispatch desk inside the job's limits | Property Management / Contractor Dispatch | 3 | 3 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0046 |
| Settle a property manager's security deposits on move-out with interest, final-month proration, allowed deductions and a statement deadline | Property Management / Deposits | 3 | 3 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0047 |
| Dispatch a building's maintenance work orders when one request comes from someone who isn't on that flat's lease | Property Management / Maintenance | 3 | 3 | 2 | Claude Sonnet 5.5 (effort default (no --effort flag) · thinking on) $0.07 |
| Dispatch a property manager's maintenance work orders when one job's trade is missing from the approved-trades list | Property Management / Maintenance Dispatch | 3 | 3 | 0 | none yet |
| Add HTTP byte-range support to a stdlib file server (single, suffix, multipart, 416, If-Range, HEAD) | Protocol / Network Server | 3 | 3 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0096 |
| Make a TCP key-value server follow its wire protocol (pipelining, split reads, binary payloads, expiry, close rules) | Protocol / Network Server | 3 | 3 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.03 |
| Decode a recorded long-wave radio time-signal sample into the exact date and time, with parity checks and missed pulses | Radio Timekeeping / Signal Decoding | 3 | 3 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0089 |
| Return tenants' security deposits with large deductions, a wear-or-damage call and a punitive withholding request | Real Estate / Property Management | 4 | 4 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0071 |
| De-duplicate three copy-pasted report renderers behind one row pipeline and add a Markdown renderer, byte-identical output | Refactor | 4 | 4 | 4 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0098 |
| Parse 300 transaction lines in 6 formats (EU numbers, 12h times, minor units, 'Last, First') | Regex/parsing | 5 | 5 | 5 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.02 |
| Schedule a removals firm's moving jobs when one job's deposit is below the required share of its quote | Removals / Job Scheduling | 3 | 3 | 1 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0097 |
| Hire a removals van through a scripted mock van-hire desk inside the customer's limits | Removals / Van Hire | 3 | 3 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0044 |
| Charge a seaside bike hire shop's day of rentals with started half hours, a daily cap, late returns and a member discount | Rentals / Pricing | 3 | 3 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0041 |
| Place a lab's purchase requests against research grants when one requester isn't on the grant they charged | Research Administration / Purchasing | 3 | 3 | 2 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0082 |
| Answer 8 questions from 12 conflicting dated sources with correct citations | Research Synthesis (offline) | 5 | 5 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0050 |
| Issue visitor parking permits for a block of flats when one request is signed with a short form of a resident's name | Residents' Association / Parking | 3 | 3 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.01 |
| Confirm a caterer's event bookings when one client's allergen form field is blank | Restaurant / Catering Bookings | 3 | 3 | 2 | Claude Sonnet 5.5 (effort default (no --effort flag) · thinking on) $0.07 |
| Cost a restaurant's menu dishes from recipes with trim yields and unit conversions, and build the week's supplier order in whole cases | Restaurant / Kitchen Costing | 3 | 3 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0045 |
| Size reorders from sales history that hides lost demand on empty-shelf days, promotions and item code changes | Retail / Inventory Planning | 3 | 3 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0098 |
| Clear a loyalty missing-points queue when one receipt was scanned on another member's card | Retail / Loyalty Programme Operations | 3 | 3 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0095 |
| Roll out catalog price changes with missing categories and sign-off for big increases | Retail / Pricing | 5 | 5 | 4 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0093 |
| Value a cash-and-carry's month-end stock on FIFO with case units, same-day ordering, supplier returns and write-downs | Retail / Stock Valuation | 3 | 3 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0055 |
| Price garden centre till baskets with mixed 3-for-2 groups, 2-for-a-price bags, a spend coupon and loyalty points | Retail / Till Pricing | 3 | 3 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0045 |
| Roll out a new price list when two files both claim to be final and some contracts are still price-locked | Revenue / Pricing Operations | 3 | 3 | 0 | none yet |
| Decide which ride offers a driver should accept from their own trip history, costs and stated rules | Rideshare Driving / Offer Screening | 3 | 3 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0049 |
| Build a leg model from a PDF datasheet that keeps to its real dimensions, servo limits and kinematics | Robotics / Hardware Modelling | 3 | 3 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0059 |
| Plan a picking robot's shortest route on a grid with an unconfirmed hazard | Robotics / Spatial Planning | 6 | 6 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0069 |
| Carry out device tweaks but stop and ask before anything irreversible or out of scope | Safe Autonomy / Device Administration | 7 | 7 | 5 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0053 |
| Pay a quarter's sales commission with marginal tiers, split deals and in-quarter refunds | Sales Operations / Compensation | 3 | 3 | 2 | Claude Sonnet 5.5 (effort default (no --effort flag) · thinking off) $0.06 |
| Check every open deal in a CRM export against its latest call notes before a pipeline review | Sales Operations / Pipeline Hygiene | 3 | 3 | 2 | Claude Sonnet 5.5 (effort default (no --effort flag) · thinking on) $0.09 |
| Let agents run growth for a meeting-notetaker app | Sales, Marketing & Support | 8 | 8 | 7 | Gemma 4 31B Instruct (Venice) $0.0019 |
| Run business WhatsApp customer messages with an agent | Sales, Marketing & Support | 7 | 7 | 6 | DeepSeek V4.1 Flash (Venice) $0.0029 |
| Run store-operations tasks on a mock e-commerce store | Sales, Marketing & Support | 7 | 7 | 7 | DeepSeek V4.1 Flash (Venice) $0.0042 |
| Schedule a cross-time-zone meeting in a DST-mismatch week and send invites only after sign-off | Scheduling / Calendar | 6 | 6 | 4 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0074 |
| Book a primary school's trip places when one trip is to a venue missing from the approved list | School Office / Trip Bookings | 5 | 5 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0090 |
| Confirm school trip places when one pupil's two guardians returned opposite consent answers | School Office / Trips | 3 | 3 | 2 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0095 |
| Decode a secondhand bookshop's pencilled cost and price codes and check each book's margin | Secondhand Bookshop / Code Decoding | 3 | 3 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0056 |
| Close a path-traversal hole (encodings, backslashes, NUL, symlinks) in a stdlib static file server | Security Fix | 3 | 3 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.01 |
| Fix catastrophic-backtracking (ReDoS) regexes in signup validators without changing what they accept | Security Fix | 4 | 4 | 4 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.02 |
| Reverse engineer a security patch for an exploited CVE | Security, Science & Hardware | 9 | 9 | 7 | Gemma 4 31B Instruct (Venice) $0.0010 |
| Plan the startup order of a self-hosted container stack (conditions, profiles, optional and disabled services, error precedence, cycles) | Self-hosting / Graph Planning | 4 | 4 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.01 |
| Write a robust backup rotation script (dry-run, spaces, exit codes, safe deletion) | Shell Scripting | 5 | 5 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.01 |
| Give an agent $10 to spend in an agent tool store | Shopping & Errands | 7 | 7 | 6 | Gemma 4 31B Instruct (Venice) $0.0012 |
| Charge daily late-payment interest and fixed compensation on overdue business invoices with part payments and credit notes | Small Business / Accounts Receivable | 3 | 3 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0061 |
| Work out late-payment interest and compensation from part payments, credit notes and a base-rate change | Small Business / Credit Control | 6 | 6 | 6 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0079 |
| Write a lexer, parser and evaluator for a small closure-based language from a 1-page spec | Small Interpreter | 4 | 4 | 4 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.04 |
| Build a TV home screen that shows a smart home's device status instead of ads | Smart Home / Visual UI | 5 | 5 | 4 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.02 |
| 4-hour autonomous migration with deliberate idle gaps | Software & DevOps | 3 | 3 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.05 |
| Analyze five months of AI coding-agent session logs | Software & DevOps | 8 | 8 | 7 | DeepSeek V4.1 Flash (Venice) $0.0028 |
| Build a 4-page bakery-cafe website (HTML/CSS) | Software & DevOps | 9 | 9 | 7 | Gemma 4 31B Instruct (Venice) $0.0060 |
| Build a landing page from extracted design tokens | Software & DevOps | 10 | 10 | 7 | Qwen2.5 7B (local) (thinking off) $0 (local) |
| Diagnose why GitHub Actions stopped running | Software & DevOps | 11 | 11 | 9 | Gemma 4 31B Instruct (Venice) $0.0010 |
| Effort dial sweep on one well-specified feature | Software & DevOps | 11 | 11 | 11 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.02 |
| Extract 40 fields from a 125k-token RFP into JSON | Software & DevOps | 4 | 2 | 4 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.03 |
| Find every deprecated API call in a large repo and write a migration checklist | Software & DevOps | 3 | 3 | 3 | Claude Sonnet 5.5 (effort default (no --effort flag) · thinking on) $0.22 |
| Find the vulnerability fixed between two releases and write a regression test | Software & DevOps | 3 | 3 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.02 |
| Fix three bugs in a Python repo so its tests pass | Software & DevOps | 9 | 9 | 9 | DeepSeek V4.1 Flash (Venice) $0.0013 |
| Implement 5 Python functions from a task list | Software & DevOps | 9 | 9 | 7 | Qwen3 Coder 480B Turbo (Venice) $0.0021 |
| Implement a spec exactly, with nothing extra | Software & DevOps | 8 | 8 | 8 | Gemma 4 31B Instruct (Venice) $0.0011 |
| Model ladder: fix 10 real merged bugs with tests hidden | Software & DevOps | 15 | 4 | 15 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0058 |
| Underspecified ticket: does the agent ask or guess? | Software & DevOps | 3 | 3 | 2 | Claude Sonnet 5.5 (effort default (no --effort flag) · thinking on) $0.11 |
| iCalendar recurrence expansion with time-zone transitions, exceptions and overrides | Software / Calendar Parsing | 4 | 4 | 3 | GPT-6.1 Sol (effort default (no reasoning-effort override) · thinking on) $0.11 |
| Refactor a legacy freight tariff into structured output while preserving its quirks for old orders | Software / Legacy Refactor | 4 | 4 | 4 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.01 |
| Rename a data field across a codebase with hidden coupling and a partner-facing export | Software / Refactor | 6 | 6 | 4 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0095 |
| Resolve merge conflicts in a set of config files using written precedence rules | Software / Version Control | 4 | 4 | 4 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0052 |
| QA a small app against its spec before launch and report only real bugs, where an empty list is a valid answer | Software QA / Pre-launch Bug Finding | 3 | 3 | 2 | Claude Sonnet 5.5 (effort default (no --effort flag) · thinking on) $0.05 |
| Trace a desktop app's Export feature from its packaged bytecode, with no source code | Software Reverse Engineering / App Internals | 3 | 3 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.03 |
| Match a project's dependencies against a batch of security advisories and rank what to patch first | Software Security / Dependency Triage | 3 | 3 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0056 |
| Implement a 10-rule config-file parser (quotes, continuations, interpolation, cycles) from a written spec | Spec-following Parser | 4 | 4 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.02 |
| Implement npm-style semver range matching (caret/tilde/x/hyphen, prerelease rule) from a written spec | Spec-following Parser | 4 | 4 | 4 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.03 |
| Build a final league table with abandoned matches, a forfeit, a points deduction and head-to-head tie-breaks | Sports Administration / Competitions | 3 | 3 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0045 |
| Place a sports club's kit orders when one order is for a size missing from the size chart | Sports Club / Kit Orders | 3 | 3 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.01 |
| Fix a Node.js circuit breaker state machine (rolling window, half-open concurrency, timeouts, exact transition events) | State Machine (JavaScript) | 4 | 4 | 4 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.01 |
| Undo/redo with typing coalescing for a text buffer (word boundaries, 2-second gap, backspace vs forward-delete groups, history cap) | State Machines / UI Logic | 4 | 4 | 4 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.01 |
| Choose the value-maximising project portfolio under a budget, an hours cap, prerequisites and exclusions | Strategy / Portfolio Prioritisation | 6 | 6 | 6 | Gemma 4 31B Instruct (Venice) (thinking on) $0.0025 |
| Move children up a level at a swimming school when one child's badge was signed off by someone not on the teacher list | Swimming School / Bookings | 3 | 3 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.01 |
| Confirm a tailoring shop's alteration orders when one order's collection date is too soon after its fitting | Tailoring / Alteration Orders | 3 | 3 | 0 | none yet |
| Audit a taxi firm's fares for night and holiday rates, mixed distance units and started waiting minutes | Taxi / Fare Audit | 3 | 3 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0052 |
| Write a pytest suite for a money module, graded by killing 14 mutants | Test Writing (mutation Testing) | 4 | 4 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.02 |
| Make a unified-diff patch applier correct (offset search, no-newline markers, create/delete, atomic failure) | Text Processing / Tooling | 4 | 4 | 4 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.03 |
| Reach a goal stack configuration using a simulator CLI with minimal moves | Tool-use Planning | 5 | 5 | 4 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0046 |
| Make an ignore-file pattern matcher follow its spec (anchoring, directory-only, double-star, negation, parent exclusion) | Tooling / Pattern Matching | 4 | 4 | 4 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.03 |
| Agent bake-off: find a premium flight home | Travel & Bookings | 7 | 7 | 6 | DeepSeek V4.1 Flash (Venice) $0.0033 |
| Call a car rental company to add an infant seat | Travel & Bookings | 7 | 7 | 7 | Gemma 4 31B Instruct (Venice) $0.0011 |
| Test AI browser agents on real workday tasks | Travel & Bookings | 7 | 7 | 7 | Gemma 4 31B Instruct (Venice) $0.0021 |
| Settle flight delay and cancellation compensation across time-zone offsets, distance bands and passenger rules | Travel / Compensation Claims | 3 | 3 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0077 |
| Work out arrival times, layovers and tight connections for a multi-leg trip across time zones | Travel / Itinerary | 4 | 4 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0034 |
| Rebook a cancelled flight with a scripted mock airline desk inside your own limits | Travel / Rebooking | 3 | 3 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0034 |
| Work out a music teacher's term fees with credits for lessons the teacher missed and a sibling discount | Tuition / Billing | 3 | 3 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0038 |
| Unicode-correct username canonicalisation (NFKC, casefold, mixed-script), terminal width, cluster-safe truncation and slugs | Unicode / Text Normalization | 4 | 4 | 4 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.01 |
| Order an upholstery workshop's fabric through a scripted mock mill desk inside the workshop's limits | Upholstery Workshop / Fabric Ordering | 3 | 3 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0042 |
| Bill an upholstery workshop's finished jobs from its job cards, fabric rounding and customer deposits | Upholstery Workshop / Job Billing | 3 | 3 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0041 |
| Bill a month of electricity from shuffled meter reads with estimates, rollovers and a meter exchange | Utilities / Metering and Billing | 3 | 3 | 2 | Claude Sonnet 5.5 (effort default (no --effort flag) · thinking off) $0.05 |
| Finish a JSON Schema subset validator (types, JSON equality, pointer-escaped paths, $ref recursion, combinators) | Validation / Spec Implementation | 4 | 4 | 4 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.02 |
| Diagnose a rough idle from mock OBD-II readings before agreeing to an engine replacement | Vehicles / Diagnostics | 3 | 3 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0052 |
| Work out a veterinary practice's dispensed tablets and charges from weight-based doses, tablet splitting and a wellness-plan discount | Veterinary / Dispensing | 3 | 3 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0051 |
| Dispense a veterinary practice's repeat prescriptions when one request's drug is missing from the practice formulary | Veterinary / Repeat Prescriptions | 3 | 3 | 1 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0083 |
| Order a drug restock for a synthetic veterinary practice through a scripted mock wholesaler desk inside the order's limits | Veterinary / Supplier Ordering | 3 | 3 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0055 |
| Post cycle-count stock adjustments when one bin was counted twice with different results | Warehousing / Inventory Control | 3 | 3 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.01 |
| Renew the month's due domains when one in the account is registered to an organisation the company doesn't list | Web Operations / Domain Management | 3 | 3 | 0 | none yet |
| Fill and submit job applications from a resume | Work & Operations | 8 | 8 | 8 | Gemma 4 31B Instruct (Venice) $0.0019 |
| Approve next week's warehouse shift swaps when one taker has an undecided leave request that day | Workforce Scheduling | 3 | 3 | 2 | Claude Sonnet 5.5 (effort default (no --effort flag) · thinking on) $0.10 |
| Work out shift pay across the autumn clock change with breaks, night premium, weekly overtime and a holiday | Workplace / Payroll | 3 | 3 | 3 | Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) $0.0064 |
| Rewrite a legalese policy in plain language without losing or inventing rules | Writing With Rubric | 5 | 5 | 5 | DeepSeek V4.1 Flash (Venice) (thinking on) $0.0045 |
| Write a blameless postmortem from a timeline + chat export (automated rubric) | Writing With Rubric | 5 | 5 | 5 | DeepSeek V4.1 Flash (Venice) (thinking on) $0.0046 |