{"id":"io.github.mauricekleine/nonobench","slug":"io-github-mauricekleine-nonobench","title":"Nonobench","description":"An open-source benchmark of how well LLMs solve nonogram puzzles, from 5x5 to 20x20.","version":"1.1.0","publisher":{"kind":"github","id":"mauricekleine","label":"@mauricekleine on GitHub","url":"https://github.com/mauricekleine"},"website":"https://www.nonobench.com","repository":"https://github.com/mauricekleine/nonobench","remotes":[{"type":"streamable-http","url":"https://www.nonobench.com/mcp"}],"packages":[],"published":"2026-09-29","updated":"2026-09-29","status":"online","auth":"","latency_ms":1293,"checked":"2026-11-19","uptime":100,"checks":3,"tools":[{"name":"get_leaderboard","title":"Get leaderboard","description":"Models ranked by accuracy; defaults to all effort levels for compatibility.","read_only":true},{"name":"list_providers","title":"List providers","description":"Provider ids, names, families and variant counts.","read_only":true},{"name":"list_families","title":"List families","description":"Model families, available efforts and best variants.","read_only":true},{"name":"compare_models","title":"Compare models","description":"Side-by-side core overall and per-size accuracy, cost, latency and token results for model or family names.","read_only":true},{"name":"get_model_results","title":"Get model results","description":"Accuracy, cost, latency and token use for one model, broken down by grid size.","read_only":true},{"name":"list_puzzles","title":"List puzzles","description":"The benchmark puzzles with their ids and row/column clues.","read_only":true},{"name":"get_puzzle","title":"Get puzzle","description":"One puzzle, including the clue text models were prompted with. The reference solution is only included on request; some puzzles have several valid solutions.","read_only":true},{"name":"check_solution","title":"Check solution","description":"Check a grid against a puzzle's clues, using the same rule as the benchmark grader. Reports which rows and columns do not match.","read_only":true},{"name":"get_puzzle_results","title":"Get puzzle results","description":"Per-model outcomes for one puzzle. Answers are omitted unless requested.","read_only":true},{"name":"get_model_puzzles","title":"Get model puzzles","description":"Which puzzles one model solved, missed, timed out on, or has not run.","read_only":true},{"name":"list_runs","title":"List runs","description":"Individual benchmark runs (one model on one puzzle), optionally with the raw prompt and model output.","read_only":true}],"server_info":{"name":"nonobench","title":"Nonobench","version":"1.1.0"},"category":"agents","tags":["sales"],"kind":"remote","source":"registry","submitted":{},"first_party":false,"domain_rank":null,"score":100,"indexable":true,"first_seen":"2026-09-29","stars":0,"badges":[],"sponsor":null,"page":"https://agentsindex.org/agents/io-github-mauricekleine-nonobench/"}