{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_pt6z46ysndby","handle":"nonobench","url":"https://wellknown.network/agents/nonobench","links":{"self":"https://wellknown.network/agents/nonobench/record.json","html":"https://wellknown.network/agents/nonobench","markdown":"https://wellknown.network/agents/nonobench/record.md","api":"https://wellknown.network/api/v1/agents/nonobench","status":"https://wellknown.network/api/v1/agents/nonobench/status","claim":"https://wellknown.network/agents/nonobench/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/nonobench/claim.json","badge":"https://wellknown.network/agents/nonobench/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/nonobench/history","tools":"https://wellknown.network/api/v1/agents/nonobench/tools"},"ard":{"identifier":"urn:air:www.nonobench.com:server:nonobench","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"Nonobench","summary":"An open-source benchmark of how well LLMs solve nonogram puzzles, from 5x5 to 20x20.","description":"An open-source benchmark of how well LLMs solve nonogram puzzles, from 5x5 to 20x20.","publisher":{"name":"mauricekleine","url":null},"homepage":"https://www.nonobench.com","repository":"https://github.com/mauricekleine/nonobench","version":"1.1.0","license":null,"protocols":["mcp"],"tags":[],"pricing":null,"endpoints":[{"url":"https://www.nonobench.com/mcp","type":"mcp_streamable_http","auth":null,"probeable":true}],"skills":null,"tools":null,"extra":{"updatedAt":"2026-09-29T22:16:28.233393Z","publishedAt":"2026-09-29T22:16:28.233393Z","registryName":"io.github.mauricekleine/nonobench"},"attribution":{"kind":"mcp_registry","name":"mcp_registry","repoUrl":"mcp_registry","summary":"mcp_registry","version":"mcp_registry","description":"mcp_registry","homepageUrl":"mcp_registry","publisherName":"mcp_registry"}},"derived":{"capabilities":[{"slug":"ai.evaluation","name":"Evaluation & Benchmarks","confidence":0.964,"provenance":"derived"},{"slug":"dev.docs-lookup","name":"Documentation Lookup","confidence":0.54,"provenance":"derived"}],"categories":["ai","dev"],"language":"en"},"observed":{"status":"live","statusReason":"Responded 4h ago.","lastOkAt":"2026-10-11T22:24:01.841Z","lastProbedAt":"2026-10-11T22:24:01.841Z","statusComputedAt":"2026-10-11T22:24:38.258Z","reliability30d":{"probes":37,"successRate":1,"p50Ms":48,"basis":"service","measures":{"availability":"availability","latency":"response time","tools":"tool surface observed","summary":"Checks reached the service itself."},"checks":{"total":37,"ok":37,"authBoundaryOk":0,"serviceOk":37,"note":"Counted from the observation rows for the window, checks of the server only (HTTP, A2A card, MCP initialize). ok = authBoundaryOk + serviceOk. `probes` is the sum of daily rollups and includes registry checks, so it can differ from `total`."}},"latestObservations":[{"at":"2026-10-11T22:24:01.841Z","kind":"mcp_initialize","ok":true,"httpStatus":200,"latencyMs":34,"error":null,"detail":{"tools":[{"name":"get_leaderboard","description":"Models ranked by accuracy; defaults to all effort levels for compatibility."},{"name":"list_providers","description":"Provider ids, names, families and variant counts."},{"name":"list_families","description":"Model families, available efforts and best variants."},{"name":"compare_models","description":"Side-by-side core overall and per-size accuracy, cost, latency and token results for model or family names."},{"name":"get_model_results","description":"Accuracy, cost, latency and token use for one model, broken down by grid size."},{"name":"list_puzzles","description":"The benchmark puzzles with their ids and row/column clues."},{"name":"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."},{"name":"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."},{"name":"get_puzzle_results","description":"Per-model outcomes for one puzzle. Answers are omitted unless requested."},{"name":"get_model_puzzles","description":"Which puzzles one model solved, missed, timed out on, or has not run."},{"name":"list_runs","description":"Individual benchmark runs (one model on one puzzle), optionally with the raw prompt and model output."}],"toolCount":11,"toolsHash":"8b9bf4dcf65a0db13d1edc1d1ac0219a79dfcb2975b592531b3dc522e20bfaac","serverName":"nonobench","capabilities":["tools"],"serverVersion":"1.1.0","protocolVersion":"2025-06-18"}},{"at":"2026-10-11T16:29:45.295Z","kind":"mcp_initialize","ok":true,"httpStatus":200,"latencyMs":100,"error":null,"detail":{"tools":[{"name":"get_leaderboard","description":"Models ranked by accuracy; defaults to all effort levels for compatibility."},{"name":"list_providers","description":"Provider ids, names, families and variant counts."},{"name":"list_families","description":"Model families, available efforts and best variants."},{"name":"compare_models","description":"Side-by-side core overall and per-size accuracy, cost, latency and token results for model or family names."},{"name":"get_model_results","description":"Accuracy, cost, latency and token use for one model, broken down by grid size."},{"name":"list_puzzles","description":"The benchmark puzzles with their ids and row/column clues."},{"name":"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."},{"name":"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."},{"name":"get_puzzle_results","description":"Per-model outcomes for one puzzle. Answers are omitted unless requested."},{"name":"get_model_puzzles","description":"Which puzzles one model solved, missed, timed out on, or has not run."},{"name":"list_runs","description":"Individual benchmark runs (one model on one puzzle), optionally with the raw prompt and model output."}],"toolCount":11,"toolsHash":"8b9bf4dcf65a0db13d1edc1d1ac0219a79dfcb2975b592531b3dc522e20bfaac","serverName":"nonobench","capabilities":["tools"],"serverVersion":"1.1.0","protocolVersion":"2025-06-18"}},{"at":"2026-10-11T09:25:50.671Z","kind":"mcp_initialize","ok":true,"httpStatus":200,"latencyMs":95,"error":null,"detail":{"tools":[{"name":"get_leaderboard","description":"Models ranked by accuracy; defaults to all effort levels for compatibility."},{"name":"list_providers","description":"Provider ids, names, families and variant counts."},{"name":"list_families","description":"Model families, available efforts and best variants."},{"name":"compare_models","description":"Side-by-side core overall and per-size accuracy, cost, latency and token results for model or family names."},{"name":"get_model_results","description":"Accuracy, cost, latency and token use for one model, broken down by grid size."},{"name":"list_puzzles","description":"The benchmark puzzles with their ids and row/column clues."},{"name":"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."},{"name":"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."},{"name":"get_puzzle_results","description":"Per-model outcomes for one puzzle. Answers are omitted unless requested."},{"name":"get_model_puzzles","description":"Which puzzles one model solved, missed, timed out on, or has not run."},{"name":"list_runs","description":"Individual benchmark runs (one model on one puzzle), optionally with the raw prompt and model output."}],"toolCount":11,"toolsHash":"8b9bf4dcf65a0db13d1edc1d1ac0219a79dfcb2975b592531b3dc522e20bfaac","serverName":"nonobench","capabilities":["tools"],"serverVersion":"1.1.0","protocolVersion":"2025-06-18"}},{"at":"2026-10-11T02:22:36.533Z","kind":"mcp_initialize","ok":true,"httpStatus":200,"latencyMs":28,"error":null,"detail":{"tools":[{"name":"get_leaderboard","description":"Models ranked by accuracy; defaults to all effort levels for compatibility."},{"name":"list_providers","description":"Provider ids, names, families and variant counts."},{"name":"list_families","description":"Model families, available efforts and best variants."},{"name":"compare_models","description":"Side-by-side core overall and per-size accuracy, cost, latency and token results for model or family names."},{"name":"get_model_results","description":"Accuracy, cost, latency and token use for one model, broken down by grid size."},{"name":"list_puzzles","description":"The benchmark puzzles with their ids and row/column clues."},{"name":"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."},{"name":"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."},{"name":"get_puzzle_results","description":"Per-model outcomes for one puzzle. Answers are omitted unless requested."},{"name":"get_model_puzzles","description":"Which puzzles one model solved, missed, timed out on, or has not run."},{"name":"list_runs","description":"Individual benchmark runs (one model on one puzzle), optionally with the raw prompt and model output."}],"toolCount":11,"toolsHash":"8b9bf4dcf65a0db13d1edc1d1ac0219a79dfcb2975b592531b3dc522e20bfaac","serverName":"nonobench","capabilities":["tools"],"serverVersion":"1.1.0","protocolVersion":"2025-06-18"}},{"at":"2026-10-10T20:27:13.368Z","kind":"mcp_initialize","ok":true,"httpStatus":200,"latencyMs":33,"error":null,"detail":{"tools":[{"name":"get_leaderboard","description":"Models ranked by accuracy; defaults to all effort levels for compatibility."},{"name":"list_providers","description":"Provider ids, names, families and variant counts."},{"name":"list_families","description":"Model families, available efforts and best variants."},{"name":"compare_models","description":"Side-by-side core overall and per-size accuracy, cost, latency and token results for model or family names."},{"name":"get_model_results","description":"Accuracy, cost, latency and token use for one model, broken down by grid size."},{"name":"list_puzzles","description":"The benchmark puzzles with their ids and row/column clues."},{"name":"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."},{"name":"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."},{"name":"get_puzzle_results","description":"Per-model outcomes for one puzzle. Answers are omitted unless requested."},{"name":"get_model_puzzles","description":"Which puzzles one model solved, missed, timed out on, or has not run."},{"name":"list_runs","description":"Individual benchmark runs (one model on one puzzle), optionally with the raw prompt and model output."}],"toolCount":11,"toolsHash":"8b9bf4dcf65a0db13d1edc1d1ac0219a79dfcb2975b592531b3dc522e20bfaac","serverName":"nonobench","capabilities":["tools"],"serverVersion":"1.1.0","protocolVersion":"2025-06-18"}},{"at":"2026-10-10T13:25:11.843Z","kind":"mcp_initialize","ok":true,"httpStatus":200,"latencyMs":54,"error":null,"detail":{"tools":[{"name":"get_leaderboard","description":"Models ranked by accuracy; defaults to all effort levels for compatibility."},{"name":"list_providers","description":"Provider ids, names, families and variant counts."},{"name":"list_families","description":"Model families, available efforts and best variants."},{"name":"compare_models","description":"Side-by-side core overall and per-size accuracy, cost, latency and token results for model or family names."},{"name":"get_model_results","description":"Accuracy, cost, latency and token use for one model, broken down by grid size."},{"name":"list_puzzles","description":"The benchmark puzzles with their ids and row/column clues."},{"name":"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."},{"name":"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."},{"name":"get_puzzle_results","description":"Per-model outcomes for one puzzle. Answers are omitted unless requested."},{"name":"get_model_puzzles","description":"Which puzzles one model solved, missed, timed out on, or has not run."},{"name":"list_runs","description":"Individual benchmark runs (one model on one puzzle), optionally with the raw prompt and model output."}],"toolCount":11,"toolsHash":"8b9bf4dcf65a0db13d1edc1d1ac0219a79dfcb2975b592531b3dc522e20bfaac","serverName":"nonobench","capabilities":["tools"],"serverVersion":"1.1.0","protocolVersion":"2025-06-18"}},{"at":"2026-10-10T06:28:18.248Z","kind":"mcp_initialize","ok":true,"httpStatus":200,"latencyMs":33,"error":null,"detail":{"tools":[{"name":"get_leaderboard","description":"Models ranked by accuracy; defaults to all effort levels for compatibility."},{"name":"list_providers","description":"Provider ids, names, families and variant counts."},{"name":"list_families","description":"Model families, available efforts and best variants."},{"name":"compare_models","description":"Side-by-side core overall and per-size accuracy, cost, latency and token results for model or family names."},{"name":"get_model_results","description":"Accuracy, cost, latency and token use for one model, broken down by grid size."},{"name":"list_puzzles","description":"The benchmark puzzles with their ids and row/column clues."},{"name":"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."},{"name":"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."},{"name":"get_puzzle_results","description":"Per-model outcomes for one puzzle. Answers are omitted unless requested."},{"name":"get_model_puzzles","description":"Which puzzles one model solved, missed, timed out on, or has not run."},{"name":"list_runs","description":"Individual benchmark runs (one model on one puzzle), optionally with the raw prompt and model output."}],"toolCount":11,"toolsHash":"8b9bf4dcf65a0db13d1edc1d1ac0219a79dfcb2975b592531b3dc522e20bfaac","serverName":"nonobench","capabilities":["tools"],"serverVersion":"1.1.0","protocolVersion":"2025-06-18"}},{"at":"2026-10-10T00:28:27.895Z","kind":"mcp_initialize","ok":true,"httpStatus":200,"latencyMs":27,"error":null,"detail":{"tools":[{"name":"get_leaderboard","description":"Models ranked by accuracy; defaults to all effort levels for compatibility."},{"name":"list_providers","description":"Provider ids, names, families and variant counts."},{"name":"list_families","description":"Model families, available efforts and best variants."},{"name":"compare_models","description":"Side-by-side core overall and per-size accuracy, cost, latency and token results for model or family names."},{"name":"get_model_results","description":"Accuracy, cost, latency and token use for one model, broken down by grid size."},{"name":"list_puzzles","description":"The benchmark puzzles with their ids and row/column clues."},{"name":"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."},{"name":"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."},{"name":"get_puzzle_results","description":"Per-model outcomes for one puzzle. Answers are omitted unless requested."},{"name":"get_model_puzzles","description":"Which puzzles one model solved, missed, timed out on, or has not run."},{"name":"list_runs","description":"Individual benchmark runs (one model on one puzzle), optionally with the raw prompt and model output."}],"toolCount":11,"toolsHash":"8b9bf4dcf65a0db13d1edc1d1ac0219a79dfcb2975b592531b3dc522e20bfaac","serverName":"nonobench","capabilities":["tools"],"serverVersion":"1.1.0","protocolVersion":"2025-06-18"}},{"at":"2026-10-09T18:26:24.595Z","kind":"mcp_initialize","ok":true,"httpStatus":200,"latencyMs":213,"error":null,"detail":{"tools":[{"name":"get_leaderboard","description":"Models ranked by accuracy; defaults to all effort levels for compatibility."},{"name":"list_providers","description":"Provider ids, names, families and variant counts."},{"name":"list_families","description":"Model families, available efforts and best variants."},{"name":"compare_models","description":"Side-by-side core overall and per-size accuracy, cost, latency and token results for model or family names."},{"name":"get_model_results","description":"Accuracy, cost, latency and token use for one model, broken down by grid size."},{"name":"list_puzzles","description":"The benchmark puzzles with their ids and row/column clues."},{"name":"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."},{"name":"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."},{"name":"get_puzzle_results","description":"Per-model outcomes for one puzzle. Answers are omitted unless requested."},{"name":"get_model_puzzles","description":"Which puzzles one model solved, missed, timed out on, or has not run."},{"name":"list_runs","description":"Individual benchmark runs (one model on one puzzle), optionally with the raw prompt and model output."}],"toolCount":11,"toolsHash":"8b9bf4dcf65a0db13d1edc1d1ac0219a79dfcb2975b592531b3dc522e20bfaac","serverName":"nonobench","capabilities":["tools"],"serverVersion":"1.1.0","protocolVersion":"2025-06-18"}},{"at":"2026-10-09T12:30:09.138Z","kind":"mcp_initialize","ok":true,"httpStatus":200,"latencyMs":63,"error":null,"detail":{"tools":[{"name":"get_leaderboard","description":"Models ranked by accuracy; defaults to all effort levels for compatibility."},{"name":"list_providers","description":"Provider ids, names, families and variant counts."},{"name":"list_families","description":"Model families, available efforts and best variants."},{"name":"compare_models","description":"Side-by-side core overall and per-size accuracy, cost, latency and token results for model or family names."},{"name":"get_model_results","description":"Accuracy, cost, latency and token use for one model, broken down by grid size."},{"name":"list_puzzles","description":"The benchmark puzzles with their ids and row/column clues."},{"name":"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."},{"name":"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."},{"name":"get_puzzle_results","description":"Per-model outcomes for one puzzle. Answers are omitted unless requested."},{"name":"get_model_puzzles","description":"Which puzzles one model solved, missed, timed out on, or has not run."},{"name":"list_runs","description":"Individual benchmark runs (one model on one puzzle), optionally with the raw prompt and model output."}],"toolCount":11,"toolsHash":"8b9bf4dcf65a0db13d1edc1d1ac0219a79dfcb2975b592531b3dc522e20bfaac","serverName":"nonobench","capabilities":["tools"],"serverVersion":"1.1.0","protocolVersion":"2025-06-18"}}],"tools":[{"name":"get_leaderboard","description":"Models ranked by accuracy; defaults to all effort levels for compatibility."},{"name":"list_providers","description":"Provider ids, names, families and variant counts."},{"name":"list_families","description":"Model families, available efforts and best variants."},{"name":"compare_models","description":"Side-by-side core overall and per-size accuracy, cost, latency and token results for model or family names."},{"name":"get_model_results","description":"Accuracy, cost, latency and token use for one model, broken down by grid size."},{"name":"list_puzzles","description":"The benchmark puzzles with their ids and row/column clues."},{"name":"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."},{"name":"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."},{"name":"get_puzzle_results","description":"Per-model outcomes for one puzzle. Answers are omitted unless requested."},{"name":"get_model_puzzles","description":"Which puzzles one model solved, missed, timed out on, or has not run."},{"name":"list_runs","description":"Individual benchmark runs (one model on one puzzle), optionally with the raw prompt and model output."}],"package":null,"toolSurface":{"id":"ts_h2ha8759gwg4","endpointId":"ep_cawu6kvtmdf9","hash":"8b9bf4dcf65a0db13d1edc1d1ac0219a79dfcb2975b592531b3dc522e20bfaac","toolCount":11,"serverName":"nonobench","serverVersion":"1.1.0","protocolVersion":"2025-06-18","firstSeenAt":"2026-10-02T00:25:03.276Z","lastSeenAt":"2026-10-11T22:24:01.843Z","observations":37,"toolNames":["get_leaderboard","list_providers","list_families","compare_models","get_model_results","list_puzzles","get_puzzle","check_solution","get_puzzle_results","get_model_puzzles","list_runs"],"distinctSurfaces":1},"endpointFacts":[{"id":"ep_cawu6kvtmdf9","url":"https://www.nonobench.com/mcp","type":"mcp_streamable_http","factsCheckedAt":"2026-10-10T20:27:13.377Z","auth":{"observedAt":"2026-10-10T20:27:13.451Z","authRequired":false,"scheme":null,"resourceMetadata":null,"authorizationServer":null,"conformance":{"dpop":false,"rfc8414":false,"rfc9728":false,"pkceS256":false,"clientIdMetadataDocument":false,"dynamicClientRegistration":false}},"tls":{"observedAt":"2026-10-10T20:27:13.479Z","protocol":"TLSv1.3","chainValid":true,"chainError":null,"hostMatches":true,"subject":"nonobench.com","issuer":{"commonName":"WE1","organization":"Google Trust Services"},"validFrom":"2026-09-23T03:21:43.000Z","validTo":"2026-12-22T04:21:39.000Z","daysToExpiry":71,"sanCount":2,"fingerprint256":"C1:D7:5E:CE:BA:CB:32:DA:89:A2:AB:13:60:9A:D8:C3:B8:CC:99:10:07:91:5F:7C:14:20:B5:BB:73:DE:AA:A0"}}]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"mcp_registry","key":"io.github.mauricekleine/nonobench","url":"https://registry.modelcontextprotocol.io/v0/servers/io.github.mauricekleine%2Fnonobench","firstSeenAt":"2026-10-02T00:18:10.599Z","fetchedAt":"2026-10-10T16:21:52.940Z","normalizedAt":"2026-10-10T16:21:52.940Z"}]},"firstSeenAt":"2026-10-02T00:18:10.599Z","updatedAt":"2026-10-11T22:25:45.351Z"}