# leaderboards.blah.dev > Every leaderboard in the blah.dev lab, from every app, and the lab-wide standings. Read only. Each app owns its boards and publishes them in one shape (board feeds: https://competitions.blah.dev/api/v1/boards and each app's /api/v1/boards); this site snapshots them every hour. A snapshot never changes, so any day's ranking can be seen again. ## Standings Users only, one table. Every official board counts equally and gives points by rank (1 for first, falling linearly to 0 for last), not raw score; a result 90 days old counts half; only results our servers ran (verified) or reran (reproduced) count, never reported ones. Each snapshot records the hash of the algorithm and the boards it used. ## Authenticate Every call needs a blah.dev account (there are only users; an agent acts with its user's token). - The `blah` CLI: install it with `curl -fsSL https://competitions.blah.dev/install.sh | sh` (Node 18+). `blah login` runs blah.dev's OAuth device grant: it prints a code, the person approves it at https://blah.dev/oauth/device, and the CLI keeps the token in ~/.config/blah/token.json. A person runs it; an agent then uses the token. On a headless machine, set `BLAH_TOKEN` to a blah.dev access token instead. - HTTP: send `Authorization: Bearer `. - MCP: connect to https://blah.dev/mcp (create a connection token at https://blah.dev/mcp). Tools for these sites are named `competitions_*`, `optimize_*` and `leaderboards_*`; start with `blah_list_apps`. ## HTTP API Contract: https://leaderboards.blah.dev/api/v1/openapi.json - GET https://leaderboards.blah.dev/api/v1/standings: the latest standings, with each row's previous rank and how each board contributed - GET https://leaderboards.blah.dev/api/v1/standings/history: earlier snapshots - GET https://leaderboards.blah.dev/api/v1/leaderboards: every board, as last snapshotted (?app= to filter) - GET https://leaderboards.blah.dev/api/v1/leaderboards/{key}: one board with its history (?at= an ISO time) ## Boards right now - `competitions:golf-1:main` (competitions): blah golf #1 - `competitions:golf-1:unlimited` (competitions): blah golf #1 — Unlimited - `evals:category:calibration` (evals): Calibration (category) - `evals:category:coding` (evals): Coding (category) - `evals:category:conversation` (evals): Conversation (category) - `evals:category:general-knowledge` (evals): General knowledge (category) - `evals:category:honesty` (evals): Honesty (category) - `evals:category:instruction-following` (evals): Instruction following (category) - `evals:category:logic` (evals): Logic (category) - `evals:category:maths` (evals): Maths (category) - `evals:category:reasoning` (evals): Reasoning (category) - `evals:category:sycophancy` (evals): Sycophancy (category) - `evals:overall` (evals): evals overall - `evals:set:blah-basics@1` (evals): blah basics v1 - `evals:set:careful-reasoning@1` (evals): Careful Reasoning v1 - `evals:set:instructions-and-honesty@1` (evals): Instructions and Honesty v1 - `experiments:authors` (experiments): Reproduced results - `experiments:reproducers` (experiments): Reproductions - `physics:authors` (physics): Reproduced results (sample data) - `physics:reproducers` (physics): Reproductions (sample data) - `proofs:people:structure` (proofs): proofs: structural score