RankedAGI

Refreshed benchmark data.

Shipped the /engine page explaining the simulated-data scoring methodology and wired the hybrid v1+v2 estimator into production, backed by a cross-validation harness and a v2 factor-model estimator; refreshed model data with Terminal-Bench 2.1.

Added Opus 4.8 and Qwen 3.7 Max benchmark data and switched dev to portless run --name for worktree-friendly URLs.

Added branding assets and updated the DeepSeek price.

Added Gemini 3.5 Flash.

Added Composer 1 and optimized the icon.

Built out AI discoverability: build-time Markdown companions served via content negotiation, an llms.txt overview, site structured data and JSON-LD, and a permissive crawler signal. Expanded the sources methodology page with the composite score formula, a data-access FAQ, and simulated-evidence controls.

Added global-rank reveal: rank on hover plus tap-to-reveal on mobile, with a faster forward transition. Surfaced model size next to name and org across the homepage and admin lists, linked admin model names to their edit pages, and refreshed the model dataset.

Reworked the simulated-data UI: per-profile scoring with simulated data, soft-orange accent, simplified controls, a hover rank style with tooltip, and an icon-only columns button. Added an admin sort dropdown and collapsible sidebar, plus a benchmark dataset refresh.

Major scoring work: added v4 and v6 pairwise-Elo backends, wired v4 through admin previews and the leaderboard, and refined the V5 frontier simulation with controlled extrapolation and sparse-data handling. Redesigned the lazy-fetched simulated-data toggle with smooth transitions and a sparkle-marked cell, and added a Visualizations lab of score-decomposition variants.

Reorganized the admin Models routes and refreshed the sidebar, dashboard thresholds, and model data.

Refreshed model data and added Grok 4.3.

Added Mistral Medium 3.5 and minor UI tweaks.

Added more GPT 5.5 benchmark data.

Added Mimo open-source model data and updated the dev setup.

Refreshed benchmark data with a DeepSeek price update and asset cleanup.

Drove composite-column styling from a shared category config, routing the matrix palette and admin list through it and tinting headers by category. Added per-profile display mode (percentage or rank) with a smooth hover swap, refreshed the logo and OG image, and skipped search autofocus on touch devices.

Built the admin benchmark matrix: moved it to a top-level route, added an open-source license filter, and redesigned the dashboard around weakest-coverage models with a live contribution panel. Solved a thorny SPA-nav picker focus bug, and hardened the data layer with rolling backups and a per-file write mutex.

Refined the benchmark sheet's composite chips: a Lucide star icon for proper sizing, letter-only collapse when squeezed, and tint that follows category. Synced the dot palette to the sheet, drove profile visibility from data, unhid the Overall column publicly, and added GPT 5.5 plus Toolathlon and DesignArena Code.

A small data refresh.

Tuned the inset shadow on table surfaces.

Pinned the site footer to the viewport bottom, extracted it to its own component, and made it sticky only on the home page while tuning the table height. Fixed the model detail page width, and added Qwen 3.6 Max and Kimi K2.6 plus a data refresh.

Rebuilt the benchmark sheet as a spreadsheet-style viewport that saves without reloading, with sticky thead/tfoot separators via inset shadows, sort that respects saved patches, click-sort, and editable model-meta columns. Stopped the dev server reloading when the lab writes data files, and added a portless setup.

Built the model-form lab through many modes (Command Center, Benchmark Grid, Leaderboard Editor, Inspector, Compare, Dial, Command) with a shared live-scoring helper, then scaffolded the fill-one-benchmark-across-models sheet with sort, fill, and paste-match. Fixed the Save-all 404 by repointing forms, refined benchmark inputs, and added Muse Spark with new benchmarks.

Restructured the admin lab into tabbed sub-routes with a polished, grouped, collapsible sidebar. Added the RAGI Agentic composite and removed the legacy computedFrom system, applied the squircle style across admin buttons and the search bar, fixed a11y warnings, renamed assets to rankedagi, and added GPT 5.4 Pro.

Promoted the v3 scoring to production with its gamma curve, coverage knobs, and lab page, then sorted the public site by the configured RAGI profile. Fixed a silent delete button in the model edit dialog, rearranged benchmarks, and added Opus 4.7.

Added windowed rendering to the admin models table for better performance, and sped up admin navigation by caching JSON reads on mtime and size with hover preloading.

Made the v2 split-pane editor the canonical model editor, retiring the old edit route, with snapshot reset and forced remount on model switch. Converted the admin top nav to a collapsible left sidebar, added a read-only aesthetic preview page, and fixed RAGI benchmark visibility and a model-edit form leak.

Rebuilt RAGI Studio with live preview, a Lean scoring mode, and unified controls, redesigning the source table with ChipSelect controls and aligning its design language with the rankings preview. Standardized benchmark keys to lowercase-with-dashes, unified admin model form styling, and handled currency negatives.

Added a dedicated RAGI studio with scoring controls, added the Vending Bench 2 benchmark with currency-format support and negative values, and polished the model edit form. Refined the mobile layout: a brain icon for thinking, compact dates, tighter padding, and a hidden version badge.

Reworked the admin: redesigned the benchmarks page as a table, added delete-model and unsaved-changes warnings, persisted table sort, and replaced license/type/version dropdowns with segmented toggles plus a ThinkingEffort field. Settled column drag-and-drop after several reverts, and refined mobile table layout.

Migrated the rankings grid from an HTML table to CSS Grid with subgrid, with conditional frozen-pane and header shadows on scroll. Added drag-and-drop column reordering with persistent visibility, fixed lint and svelte-check errors across files, and improved the model edit form.

Fixed an O(N^2) DataTable bottleneck and replaced $effect anti-patterns with idiomatic Svelte 5, removed 8 unused shadcn families, and dropped date-fns for a native relative-time helper. Added benchmark archiving, model filters, and a multi-link array, unified benchmark category sort order, and centralized admin styling.

Refactored JSON data access for SvelteKit, fixed benchmark form save behavior, sorted admin models by release date while keeping edits in place, and added the GLM 5.1 model.

Made admin updates.

Added model table header sorting and a delete dialog, refactored the admin layout and styling for responsiveness and dark mode, set a 404 fallback for unknown URLs on static hosts, and sourced benchmark columns from benchmarks.json.

Dropped Supabase for local data functions, adding model helpers and a pre-sorted models.json. Adopted a new font and color stack with dark mode, moved filters to bindable state with $derived.by, and migrated to $app/state and resolve()-based navigation.

Updated the app shell.

Updated npm dependencies.

Updated the leaderboard page.

Formatting pass.

Focused the search bar on load.

Added sticky columns to the leaderboard table with a capped height and refined header styling.

Refactored table state to Svelte 5 runes.

Added the SvelteBench benchmark with a column label and visibility control.

Added an About link to the footer and fixed the heading color in dark mode.

Improved DataTable spacing for layout consistency.

Refined FilterDropdown and TableHeader styling.

Refined the table header and filter component styling and clarified the LiveBench column.

Changed the Preview badge color from yellow to fuchsia.

Reworked benchmark columns: added Humanity, swapped LiveCodeBench versions, and tuned column visibility and labels.

Removed the deprecated Aider column.

Switched the table header to a columnVisibility store for visibility control.

Reworked model filters into grouped, checkbox-based accordions with responsive mobile rendering, grouped the column selector into toggleable categories, and added a shared ChevronIcon.

Clarified the LiveBench code-column version subtitle.

Clarified the LiveBench code-column version subtitle.

Reworked the LiveBench column keys and tooltips for 2024 and 2025.

Standardized benchmark column keys to lowercase-with-underscores and added the ragi_code column.

Updated the Open Graph and Twitter images to the new OG image with better shadows.

Added MMMU and tooltip descriptions for the MMLU columns.

Moved the logo config to its own file and conditionally showed organization logos on the model page.

Clarified the About page's ownership and mission and improved the contact info.

Set an explicit icon height for display.

Rebranded from RankedAI to RankedAGI across the project and README and added the NYT Connections Extended column.

Refined model link styling for visibility in light and dark mode and added svelte-render-scan.

Updated the navigation icons.

Improved the leaderboard: better model contrast and underlines, search-bar refinements, the leaderboard in the nav, and new vendor logos.

Added categories and subcategories, logos in the Model column, and header polish.

Added nav to the homepage, a cleaner filter, and search-bar updates.

Added search inside the DataTable.

Reworded copy from we to I and polished the UI.

Expanded the README with data sources and cleaned up.

Updated the benchmark card for light mode.

Added a Sources page wired into the sitemap, plus metadata fixes.

Updated the card design for dark mode.

Added LiveCodeBench and a relative last-updated time.

Added a new benchmark and reordered GPQA and IFEval.

Refined transitions and icons.

Reworked navigation and the search bar, fixed model ordering, and cleaned up components.

Made entire cells clickable, made the sort dropdown responsive, and did Svelte 5 cleanup and UI polish.

Upgraded to Tailwind 4, made the leaderboard responsive, added model logos and an improved model page, and refined the filters and color palette.

Got filters working and prevented the browser back-gesture while scrolling.

Updated the page title.

Fixed a Safari z-index issue.

Added IndexNow.

Added AIME 2025.

Added smooth transitions and aligned sorting on the Models page.

Set up a single source of truth for site data with per-page OG and a dynamic sitemap, fixed the canonical link, and refined the card defaults and UI.

Added ranks for dates and context, reworked the cards, and polished styles.

Added a dynamic sitemap and robots, improved color contrast, and removed Ahrefs analytics.

Added more benchmarks, built out the model page, fixed multiple-H1 issues, and refreshed the footer and UI.

Added subheadings and reduced the font size.

Added AIME.

Removed the Artificial Analysis score.

Added cache-hit cost and switched the Type column to License.

Upgraded search with exclusion operators and multi-term exclusion, added verified-commit signing, and improved the dark-mode badge.

Improved sorting, trimmed duplicate H1s on the Models page, and tightened the meta descriptions.

Added WebDevArena with style control, added ranks, and tightened the UI and accessibility.

Tried a hex logo, then reverted.

Reworked the Models page and added robots.txt and Ahrefs verification.

Updated the README.

Connected Supabase as the data source, cleaned up the Airtable data, and made size sortable.

Added Cmd+K search with Windows support and refactored the search bar, added AidanBench, lazy-loaded logos, and refreshed the OG and X card metadata.

Added the SWEBench, Codeforces, and AiderPoly benchmarks and improved the wordmark in dark mode.

Added Open Graph and Twitter Card metadata.

Formatted code.

Rebranded, reordered the Hallucination column, and added a logo hover effect and a Microsoft icon.

Added more benchmarks.

Split the logo wordmark into its own component.

Updated the version badge.

Consolidated code and fixed a unique-column bug.

Updated styles.

Fixed font linking.

Added Amazon logos, five ranks, and clear-search on Esc.

Switched numbers to a mono font and moved all logos to SVG.

Marked the version as Beta.

Updated the icon.

Updated analytics and security headers.

Migrated from Svelte 4 to 5, added tooltips and analytics, and refreshed the UI and icons.

Restructured the page and removed search autofocus.

Added a release-type column with conditional styling and UI improvements.

Updated the leaderboard page.

Updated the env example and UI.

Built a git-commit-based versioning system after several iterations, applied production-only security headers, and refreshed the UI and rebranding.

Polished UI symmetry.

Optimized ranking, separated the formatters, added release dates and logos, and cleaned up.

Built out the leaderboard with dark mode, a responsive layout, logos, a favicon, and SEO.

Started the project with an initial commit.