Server definition
- Hash
- sha256:d1051613101a5b239a87a16a7ccb9085d04ab905aad7b14852b47741adc1661e
- What it is
- What a remote MCP server returned when asked what it offers: 11 tools
The blob, as servednamed by its sha256
{
"instructions": "Nonobench measures how well LLMs solve nonogram (picross) puzzles: 40 puzzles across 5x5, 10x10, 15x15, 20x20 grids. Standard is 5x5, 10x10 and 15x15, and overall accuracy covers those 30 puzzles. Hard mode is ten 20x20 puzzles, reported only per size (size \"20x20\"). Accuracy is the share of puzzles where the model's grid satisfies every row and column clue. Results last updated 2026-09-30T06:04:32.234Z.",
"tools": [
{
"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.",
"inputSchema": {
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {
"grid": {
"description": "Row-major string of 0 (empty) and 1 (filled), width × height characters",
"type": "string"
},
"id": {
"description": "Puzzle id from list_puzzles",
"type": "string"
}
},
"required": [
"id",
"grid"
],
"type": "object"
},
"name": "check_solution",
"outputSchema": {
"$schema": "https://json-schema.org/draft/2020-12/schema",
"additionalProperties": {},
"properties": {
"columnViolations": {
"items": {},
"type": "array"
},
"correct": {
"type": "boolean"
},
"error": {
"type": "string"
},
"rowViolations": {
"items": {},
"type": "array"
}
},
"required": [
"correct",
"rowViolations",
"columnViolations"
],
"type": "object"
}
},
{
"description": "Side-by-side core overall and per-size accuracy, cost, latency and token results for model or family names.",
"inputSchema": {
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {
"models": {
"description": "2 to 20 model variant ids or family names, e.g. claude-opus-5.5 or gpt-6-astra-xhigh",
"items": {
"type": "string"
},
"maxItems": 20,
"minItems": 2,
"type": "array"
}
},
"required": [
"models"
],
"type": "object"
},
"name": "compare_models",
"outputSchema": {
"$schema": "https://json-schema.org/draft/2020-12/schema",
"additionalProperties": false,
"properties": {
"models": {
"items": {
"additionalProperties": {},
"properties": {
"accuracy": {
"description": "Percentage of puzzles solved",
"type": "number"
},
"bySize": {
"items": {
"additionalProperties": {},
"properties": {
"size": {
"type": "string"
}
},
"required": [
"size"
],
"type": "object"
},
"type": "array"
},
"correct": {
"type": "number"
},
"displayName": {
"type": "string"
},
"effort": {
"type": [
"string",
"null"
]
},
"failedRuns": {
"type": "number"
},
"family": {
"type": "string"
},
"model": {
"description": "Model variant id, e.g. claude-opus-5.5-high",
"type": "string"
},
"provider": {
"type": [
"string",
"null"
]
},
"reasoning": {
"type": "boolean"
},
"total": {
"type": "number"
}
},
"required": [
"model",
"displayName",
"family",
"effort",
"provider",
"reasoning",
"accuracy",
"correct",
"total",
"failedRuns",
"bySize"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"models"
],
"type": "object"
}
},
{
"description": "Models ranked by accuracy; defaults to all effort levels for compatibility.",
"inputSchema": {
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {
"effort": {
"description": "best, all (default), or one effort level; empty means all",
"type": "string"
},
"family": {
"description": "Comma-separated family ids; empty means no filter",
"type": "string"
},
"min_correct": {
"description": "Minimum puzzles solved in the selected tier; default 0 includes unsolved variants",
"maximum": 9007199254740991,
"minimum": 0,
"type": "integer"
},
"open_weights": {
"description": "Only open-weight (true) or closed (false) models",
"type": "boolean"
},
"provider": {
"description": "Comma-separated provider ids; empty means no filter",
"type": "string"
},
"reasoning": {
"description": "Only reasoning (true) or non-reasoning (false) variants",
"type": "boolean"
},
"size": {
"description": "Grid size to filter on",
"enum": [
"5x5",
"10x10",
"15x15",
"20x20"
],
"type": "string"
},
"version": {
"description": "Comma-separated benchmark versions: 1.0, 1.1, 1.2; empty means all",
"type": "string"
}
},
"type": "object"
},
"name": "get_leaderboard",
"outputSchema": {
"$schema": "https://json-schema.org/draft/2020-12/schema",
"additionalProperties": false,
"properties": {
"models": {
"items": {
"additionalProperties": {},
"properties": {
"accuracy": {
"description": "Percentage of puzzles solved",
"type": "number"
},
"correct": {
"type": "number"
},
"displayName": {
"type": "string"
},
"effort": {
"type": [
"string",
"null"
]
},
"family": {
"type": "string"
},
"model": {
"description": "Model variant id, e.g. claude-opus-5.5-high",
"type": "string"
},
"provider": {
"type": [
"string",
"null"
]
},
"rank": {
"type": "number"
},
"reasoning": {
"type": "boolean"
},
"total": {
"type": "number"
},
"totalCostUsd": {
"type": "number"
}
},
"required": [
"model",
"displayName",
"family",
"effort",
"provider",
"reasoning",
"accuracy",
"rank",
"correct",
"total",
"totalCostUsd"
],
"type": "object"
},
"type": "array"
},
"size": {
"type": "string"
},
"updatedAt": {
"type": "string"
}
},
"required": [
"updatedAt",
"size",
"models"
],
"type": "object"
}
},
{
"description": "Which puzzles one model solved, missed, timed out on, or has not run.",
"inputSchema": {
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {
"model": {
"description": "Model variant id as listed on the leaderboard, e.g. claude-opus-5.5-high",
"type": "string"
}
},
"required": [
"model"
],
"type": "object"
},
"name": "get_model_puzzles",
"outputSchema": {
"$schema": "https://json-schema.org/draft/2020-12/schema",
"additionalProperties": false,
"properties": {
"attempted": {
"type": "number"
},
"displayName": {
"type": "string"
},
"model": {
"type": "string"
},
"puzzles": {
"items": {
"additionalProperties": {},
"properties": {
"id": {
"type": "string"
},
"index": {
"type": "number"
},
"size": {
"type": "string"
},
"state": {
"enum": [
"solved",
"wrong",
"cut-off",
"not-run"
],
"type": "string"
}
},
"required": [
"id",
"index",
"size",
"state"
],
"type": "object"
},
"type": "array"
},
"solved": {
"type": "number"
}
},
"required": [
"model",
"displayName",
"solved",
"attempted",
"puzzles"
],
"type": "object"
}
},
{
"description": "Accuracy, cost, latency and token use for one model, broken down by grid size.",
"inputSchema": {
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {
"model": {
"description": "Model name as listed on the leaderboard, e.g. gpt-5.4-xhigh",
"type": "string"
}
},
"required": [
"model"
],
"type": "object"
},
"name": "get_model_results",
"outputSchema": {
"$schema": "https://json-schema.org/draft/2020-12/schema",
"additionalProperties": {},
"properties": {
"accuracy": {
"description": "Percentage of puzzles solved",
"type": "number"
},
"bySize": {
"items": {
"additionalProperties": {},
"properties": {
"size": {
"type": "string"
}
},
"required": [
"size"
],
"type": "object"
},
"type": "array"
},
"correct": {
"type": "number"
},
"displayName": {
"type": "string"
},
"effort": {
"type": [
"string",
"null"
]
},
"failedRuns": {
"type": "number"
},
"family": {
"type": "string"
},
"model": {
"description": "Model variant id, e.g. claude-opus-5.5-high",
"type": "string"
},
"provider": {
"type": [
"string",
"null"
]
},
"reasoning": {
"type": "boolean"
},
"total": {
"type": "number"
}
},
"required": [
"model",
"displayName",
"family",
"effort",
"provider",
"reasoning",
"accuracy",
"correct",
"total",
"failedRuns",
"bySize"
],
"type": "object"
}
},
{
"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.",
"inputSchema": {
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {
"id": {
"description": "Puzzle id from list_puzzles",
"type": "string"
},
"include_solution": {
"description": "Include a reference solution",
"type": "boolean"
}
},
"required": [
"id"
],
"type": "object"
},
"name": "get_puzzle",
"outputSchema": {
"$schema": "https://json-schema.org/draft/2020-12/schema",
"additionalProperties": {},
"properties": {
"columnClues": {
"items": {
"items": {
"type": "number"
},
"type": "array"
},
"type": "array"
},
"height": {
"type": "number"
},
"id": {
"type": "string"
},
"index": {
"type": "number"
},
"prompt": {
"description": "Clue text as models received it",
"type": "string"
},
"referenceSolution": {
"type": "string"
},
"rowClues": {
"items": {
"items": {
"type": "number"
},
"type": "array"
},
"type": "array"
},
"size": {
"type": "string"
},
"url": {
"type": "string"
},
"width": {
"type": "number"
}
},
"required": [
"id",
"index",
"size",
"width",
"height",
"rowClues",
"columnClues",
"url",
"prompt"
],
"type": "object"
}
},
{
"description": "Per-model outcomes for one puzzle. Answers are omitted unless requested.",
"inputSchema": {
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {
"effort": {
"description": "best, all (default), or one effort level",
"type": "string"
},
"family": {
"description": "Comma-separated family ids; empty means no filter",
"type": "string"
},
"id": {
"description": "Puzzle id from list_puzzles",
"type": "string"
},
"include_answers": {
"description": "Include each model's answer grid",
"type": "boolean"
},
"open_weights": {
"description": "Only open-weight (true) or closed (false) models",
"type": "boolean"
},
"provider": {
"description": "Comma-separated provider ids; empty means no filter",
"type": "string"
},
"reasoning": {
"description": "Only reasoning (true) or non-reasoning (false) variants",
"type": "boolean"
}
},
"required": [
"id"
],
"type": "object"
},
"name": "get_puzzle_results",
"outputSchema": {
"$schema": "https://json-schema.org/draft/2020-12/schema",
"additionalProperties": false,
"properties": {
"attempts": {
"type": "number"
},
"index": {
"type": "number"
},
"puzzleId": {
"type": "string"
},
"runs": {
"items": {
"additionalProperties": {},
"properties": {
"answer": {
"type": [
"string",
"null"
]
},
"correct": {
"type": "boolean"
},
"displayName": {
"type": "string"
},
"model": {
"type": "string"
},
"status": {
"type": "string"
}
},
"required": [
"model",
"correct",
"status",
"displayName"
],
"type": "object"
},
"type": "array"
},
"size": {
"type": "string"
},
"solved": {
"type": "number"
},
"updatedAt": {
"type": "string"
}
},
"required": [
"updatedAt",
"puzzleId",
"index",
"size",
"attempts",
"solved",
"runs"
],
"type": "object"
}
},
{
"description": "Model families, available efforts and best variants.",
"inputSchema": {
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {},
"type": "object"
},
"name": "list_families",
"outputSchema": {
"$schema": "https://json-schema.org/draft/2020-12/schema",
"additionalProperties": false,
"properties": {
"families": {
"items": {
"additionalProperties": {},
"properties": {
"bestVariant": {
"type": "string"
},
"displayName": {
"type": "string"
},
"efforts": {
"items": {
"type": "string"
},
"type": "array"
},
"family": {
"type": "string"
},
"provider": {
"type": [
"string",
"null"
]
}
},
"required": [
"family",
"displayName",
"provider",
"bestVariant",
"efforts"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"families"
],
"type": "object"
}
},
{
"description": "Provider ids, names, families and variant counts.",
"inputSchema": {
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {},
"type": "object"
},
"name": "list_providers",
"outputSchema": {
"$schema": "https://json-schema.org/draft/2020-12/schema",
"additionalProperties": false,
"properties": {
"providers": {
"items": {
"additionalProperties": {},
"properties": {
"families": {
"items": {
"type": "string"
},
"type": "array"
},
"id": {
"type": "string"
},
"name": {
"type": "string"
},
"variantCount": {
"type": "number"
}
},
"required": [
"id",
"name",
"variantCount",
"families"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"providers"
],
"type": "object"
}
},
{
"description": "The benchmark puzzles with their ids and row/column clues.",
"inputSchema": {
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {
"size": {
"description": "Grid size to filter on",
"enum": [
"5x5",
"10x10",
"15x15",
"20x20"
],
"type": "string"
}
},
"type": "object"
},
"name": "list_puzzles",
"outputSchema": {
"$schema": "https://json-schema.org/draft/2020-12/schema",
"additionalProperties": false,
"properties": {
"puzzles": {
"items": {
"additionalProperties": {},
"properties": {
"columnClues": {
"items": {
"items": {
"type": "number"
},
"type": "array"
},
"type": "array"
},
"height": {
"type": "number"
},
"id": {
"type": "string"
},
"index": {
"type": "number"
},
"rowClues": {
"items": {
"items": {
"type": "number"
},
"type": "array"
},
"type": "array"
},
"size": {
"type": "string"
},
"url": {
"type": "string"
},
"width": {
"type": "number"
}
},
"required": [
"id",
"index",
"size",
"width",
"height",
"rowClues",
"columnClues",
"url"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"puzzles"
],
"type": "object"
}
},
{
"description": "Individual benchmark runs (one model on one puzzle), optionally with the raw prompt and model output.",
"inputSchema": {
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {
"include_output": {
"description": "Include raw prompt and model output (large)",
"type": "boolean"
},
"limit": {
"description": "Default 100",
"maximum": 500,
"minimum": 1,
"type": "integer"
},
"model": {
"description": "Only runs of this model variant id",
"type": "string"
},
"offset": {
"description": "Runs to skip, for paging; default 0",
"maximum": 9007199254740991,
"minimum": 0,
"type": "integer"
},
"puzzle_id": {
"description": "Only runs on this puzzle id from list_puzzles",
"type": "string"
},
"size": {
"description": "Grid size to filter on",
"enum": [
"5x5",
"10x10",
"15x15",
"20x20"
],
"type": "string"
}
},
"type": "object"
},
"name": "list_runs",
"outputSchema": {
"$schema": "https://json-schema.org/draft/2020-12/schema",
"additionalProperties": false,
"properties": {
"limit": {
"type": "number"
},
"offset": {
"type": "number"
},
"runs": {
"items": {
"additionalProperties": {},
"properties": {
"correct": {
"type": "boolean"
},
"model": {
"type": "string"
},
"puzzleId": {
"type": "string"
},
"size": {
"type": "string"
},
"status": {
"type": "string"
}
},
"required": [
"model",
"puzzleId",
"size",
"correct",
"status"
],
"type": "object"
},
"type": "array"
},
"total": {
"type": "number"
}
},
"required": [
"total",
"limit",
"offset",
"runs"
],
"type": "object"
}
}
]
}Verify it yourself
curl -s https://api.teppi.xyz/v1/evidence/sha256:d1051613101a5b239a87a16a7ccb9085d04ab905aad7b14852b47741adc1661e | sha256sum