Generative Capability

Feature delivery, build reliability, and generated app galleries.

The broad historical reference runs, not the later one-case diagnostics. These use modeled/mock generation and are not empirical evidence of current agent performance. Each track retains its own date, model labels and scoring history.

Models & settings — click to expand

Completeness by final feature-list position

Bins summarize checks by final feature-list position, not elapsed time or observed completion milestones.

Feature completeness by harness

Recorded feature completeness · bootstrap 95% CI whiskers stay attached to their harness

Generative dimensions

build · completeness · visual · plan/trajectory · honesty

Side-by-side app gallery

App explorer

Click a row for the feature checklist, the milestone plan, and scores. Red outline = claimed-but-failed (dishonest).
AppHarnessLangBuildCompletenessPlanHonesty

Inspect the evidence

Inside the dataset

3 items
ecommerceE-commerce storefronttypescript
Build a production-grade e-commerce storefront end-to-end. Shoppers browse a paginated product catalog, search and filter by category, open a product detail page, add items to a persistent cart, and check out through a validated form that creates a Stripe payment intent and writes an order to the database. Registered users can sign up, log in (session cookie), and view order history; an admin area supports product CRUD. Treat this as a real, multi-stage build: schema and migrations first, then API routes, then UI, then auth and admin, with tests at each layer.
  • product-list
  • product-detail
  • search
  • filters
  • cart-add
  • cart-update
  • checkout-form
  • payment
  • order-confirm
  • auth-signup
  • auth-login
  • admin-products
Open scored results ↓
chat-cloneChatGPT clonetypescript
Build a ChatGPT-style assistant app. The UI is a chat shell with a composer and a scrolling message list; sending a message calls the backend, which streams the assistant reply token-by-token over Server-Sent Events. A sidebar lists past conversations and lets the user start, switch, and delete threads; history persists across reloads. Messages render markdown with highlighted code blocks; users can regenerate the last reply and adjust model/temperature in settings. Anonymous users are gated behind auth. Build incrementally with tests for the API, streaming, and persistence layers.
  • chat-ui
  • send-message
  • stream
  • conversation-list
  • new-conversation
  • markdown
  • code-highlight
  • persist
  • auth
  • regenerate
  • delete
  • settings
Open scored results ↓
dashboardAnalytics dashboardpython
Build a role-gated analytics dashboard. A typed FastAPI service exposes metrics endpoints backed by Postgres; the React frontend renders KPI summary cards, an interactive time-series chart, and a sortable, paginated data table, all driven by a date-range filter. Users can export the current view as CSV and drill into a detail view. Access is authenticated and role-gated: viewers can read but not edit; data auto-refreshes on an interval. Deliver the API (with OpenAPI types) first, then the frontend, with tests for the endpoints, the filter logic, and role gating.
  • metrics-api
  • timeseries
  • kpi-cards
  • date-filter
  • data-table
  • csv-export
  • auth
  • role-gating
  • realtime
  • drilldown
Open scored results ↓

Inspect the evidence

Explore experiments

11 items