{"ok":true,"site":{"host":"nonobench.com","url":"https://www.nonobench.com/","type":"live","desc":"Evaluate and compare how well large language models solve Nonogram (Picross) puzzles. Interactive benchmark results, visualizations, and leaderboards for AI reasoning capabilities.","tools":[{"name":"get_leaderboard","kind":"answer","impl":"imperative","description":"Nonobench models ranked by accuracy, overall or for one grid size. Effort defaults to all levels; use effort=best to match the homepage.","annotations":{"readOnlyHint":true},"inputSchema":{"type":"object","properties":{"size":{"type":"string","enum":["5x5","10x10","15x15","20x20"],"description":"Grid size to filter on"},"provider":{"type":"string","description":"Comma-separated provider ids"},"family":{"type":"string","description":"Comma-separated family ids"},"version":{"type":"string","description":"Comma-separated benchmark versions: 1.0, 1.1, 1.2"},"effort":{"type":"string","description":"best, all, or an effort level"},"reasoning":{"type":"boolean"},"open_weights":{"type":"boolean"}}},"hasHandler":true,"hasExecute":true,"__source":"spec","executable":true,"handlerField":"execute","page":"/","pages":["/","/how-it-works","/puzzles"]},{"name":"list_providers","kind":"answer","impl":"imperative","description":"Provider ids, names, families and variant counts.","annotations":{"readOnlyHint":true},"inputSchema":{"type":"object","properties":{}},"hasHandler":true,"hasExecute":true,"__source":"spec","executable":true,"handlerField":"execute","page":"/","pages":["/","/how-it-works","/puzzles"]},{"name":"list_families","kind":"answer","impl":"imperative","description":"Model families, efforts and best variants.","annotations":{"readOnlyHint":true},"inputSchema":{"type":"object","properties":{}},"hasHandler":true,"hasExecute":true,"__source":"spec","executable":true,"handlerField":"execute","page":"/","pages":["/","/how-it-works","/puzzles"]},{"name":"compare_models","kind":"act","impl":"imperative","description":"Compare two or more model ids or family names side by side.","annotations":{"readOnlyHint":true},"inputSchema":{"type":"object","properties":{"models":{"type":"array","items":{"type":"string"},"minItems":2}},"required":["models"]},"hasHandler":true,"hasExecute":true,"__source":"spec","executable":true,"handlerField":"execute","page":"/","pages":["/","/how-it-works","/puzzles"]},{"name":"set_filters","kind":"act","impl":"imperative","description":"Update the visible leaderboard filters and URL.","inputSchema":{"type":"object","properties":{"size":{"type":"string","enum":["5x5","10x10","15x15","20x20"],"description":"Grid size to filter on"},"provider":{"type":"string","description":"Comma-separated provider ids"},"family":{"type":"string","description":"Comma-separated family ids"},"version":{"type":"string","description":"Comma-separated benchmark versions: 1.0, 1.1, 1.2"},"effort":{"type":"string","description":"best, all, or an effort level"},"reasoning":{"type":"boolean"},"open_weights":{"type":"boolean"}}},"hasHandler":true,"hasExecute":true,"__source":"spec","executable":true,"handlerField":"execute","page":"/","pages":["/","/how-it-works","/puzzles"]},{"name":"get_model_results","kind":"answer","impl":"imperative","description":"Accuracy, cost and latency for one model, per grid size.","annotations":{"readOnlyHint":true},"inputSchema":{"type":"object","properties":{"model":{"type":"string","description":"Model name from the leaderboard"}},"required":["model"]},"hasHandler":true,"hasExecute":true,"__source":"spec","executable":true,"handlerField":"execute","page":"/","pages":["/","/how-it-works","/puzzles"]},{"name":"list_puzzles","kind":"answer","impl":"imperative","description":"The benchmark puzzles with ids and row/column clues.","annotations":{"readOnlyHint":true},"inputSchema":{"type":"object","properties":{"size":{"type":"string","enum":["5x5","10x10","15x15","20x20"],"description":"Grid size to filter on"}}},"hasHandler":true,"hasExecute":true,"__source":"spec","executable":true,"handlerField":"execute","page":"/","pages":["/","/how-it-works","/puzzles"]},{"name":"get_puzzle_results","kind":"answer","impl":"imperative","description":"Per-model outcomes for a puzzle, optionally including parsed grids.","annotations":{"readOnlyHint":true},"inputSchema":{"type":"object","properties":{"id":{"type":"string"},"size":{"type":"string","enum":["5x5","10x10","15x15","20x20"],"description":"Grid size to filter on"},"provider":{"type":"string","description":"Comma-separated provider ids"},"family":{"type":"string","description":"Comma-separated family ids"},"version":{"type":"string","description":"Comma-separated benchmark versions: 1.0, 1.1, 1.2"},"effort":{"type":"string","description":"best, all, or an effort level"},"reasoning":{"type":"boolean"},"open_weights":{"type":"boolean"},"include_answers":{"type":"boolean"}},"required":["id"]},"hasHandler":true,"hasExecute":true,"__source":"spec","executable":true,"handlerField":"execute","page":"/","pages":["/","/how-it-works","/puzzles"]},{"name":"get_model_puzzles","kind":"answer","impl":"imperative","description":"Which puzzles a model solved, missed, or did not run.","annotations":{"readOnlyHint":true},"inputSchema":{"type":"object","properties":{"model":{"type":"string"}},"required":["model"]},"hasHandler":true,"hasExecute":true,"__source":"spec","executable":true,"handlerField":"execute","page":"/","pages":["/","/how-it-works","/puzzles"]},{"name":"check_solution","kind":"answer","impl":"imperative","description":"Check a nonogram grid (row-major 0/1 string) against a puzzle's clues.","annotations":{"readOnlyHint":true},"inputSchema":{"type":"object","properties":{"id":{"type":"string","description":"Puzzle id"},"grid":{"type":"string"}},"required":["id","grid"]},"hasHandler":true,"hasExecute":true,"__source":"spec","executable":true,"handlerField":"execute","page":"/","pages":["/","/how-it-works","/puzzles"]},{"name":"open_puzzle","kind":"act","impl":"imperative","description":"Show a puzzle in the puzzle explorer on this page.","inputSchema":{"type":"object","properties":{"index":{"type":"integer","minimum":0,"maximum":39,"description":"0-based puzzle index from list_puzzles"},"model":{"type":"string","description":"Optional model variant to show its answer overlay"}},"required":["index"]},"hasHandler":true,"hasExecute":true,"__source":"spec","executable":true,"handlerField":"execute","page":"/","pages":["/","/how-it-works","/puzzles"]}],"category":"AI & Agents","favicon":"/favicons/nonobench.com.png","apiSurface":"spec","toolCount":11}}