An open-source benchmark of how well LLMs solve nonogram puzzles, from 5x5 to 20x20.
Connect Remote server
claude mcp add --transport http nonobench https://www.nonobench.com/mcp
{
"mcpServers": {
"nonobench": {
"url": "https://www.nonobench.com/mcp"
}
}
}
{
"servers": {
"nonobench": {
"type": "http",
"url": "https://www.nonobench.com/mcp"
}
}
}
Settings > Connectors > Add custom connector
URL: https://www.nonobench.com/mcp
Tools 11 found in our last check
get_leaderboardModels ranked by accuracy; defaults to all effort levels for compatibility.
list_providersProvider ids, names, families and variant counts.
list_familiesModel families, available efforts and best variants.
compare_modelsSide-by-side core overall and per-size accuracy, cost, latency and token results for model or family names.
get_model_resultsAccuracy, cost, latency and token use for one model, broken down by grid size.
list_puzzlesThe benchmark puzzles with their ids and row/column clues.
get_puzzleOne puzzle, including the clue text models were prompted with. The reference solution is only included on request; some puzzles have several valid solutions.
check_solutionCheck a grid against a puzzle's clues, using the same rule as the benchmark grader. Reports which rows and columns do not match.
get_puzzle_resultsPer-model outcomes for one puzzle. Answers are omitted unless requested.
get_model_puzzlesWhich puzzles one model solved, missed, timed out on, or has not run.
list_runsIndividual benchmark runs (one model on one puzzle), optionally with the raw prompt and model output.
Details
| Endpoint | https://www.nonobench.com/mcp (Streamable HTTP) |
| First published | 29 Sep 2026 |
| Last updated | 29 Sep 2026 |
| Registry name | io.github.mauricekleine/nonobench |
More ai and media servers See all
Listing data from the official MCP registry. Status and tools from NestDaddy's daily check. Browse all MCP servers.
