← WebMCP Directory

Tool tree

jev-bench.cocode.dk

AI & AgentsTools verified
Website
Jev Bench is an open classifier workbench: compare API latency and label accuracy with repeatable datasets, named models, and downloadable results.
Explore capabilities

    page: Home

    describeAnswer

    Describe the Jev Bench results page, its selected experiment, and available controls.

    View tool JSON
    {
  "name": "describe",
  "kind": "answer",
  "impl": "imperative",
  "description": "Describe the Jev Bench results page, its selected experiment, and available controls.",
  "inputSchema": {
    "type": "object",
    "properties": {},
    "required": [],
    "additionalProperties": false
  },
  "page": "/"
}
    list_runsAnswer

    List the published classification experiments available in the page's experiment selector.

    View tool JSON
    {
  "name": "list_runs",
  "kind": "answer",
  "impl": "imperative",
  "description": "List the published classification experiments available in the page's experiment selector.",
  "inputSchema": {
    "type": "object",
    "properties": {},
    "required": [],
    "additionalProperties": false
  },
  "page": "/"
}
    get_resultsAnswer

    Read the selected experiment's latency, accuracy, error counts, and returned model names.

    View tool JSON
    {
  "name": "get_results",
  "kind": "answer",
  "impl": "imperative",
  "description": "Read the selected experiment's latency, accuracy, error counts, and returned model names.",
  "inputSchema": {
    "type": "object",
    "properties": {},
    "required": [],
    "additionalProperties": false
  },
  "page": "/"
}
    select_runAction

    Select a published experiment and return the results now displayed on the page.

    View tool JSON
    {
  "name": "select_run",
  "kind": "act",
  "impl": "imperative",
  "description": "Select a published experiment and return the results now displayed on the page.",
  "inputSchema": {
    "type": "object",
    "properties": {
      "run_id": {
        "type": "string"
      }
    },
    "required": [
      "run_id"
    ],
    "additionalProperties": false
  },
  "page": "/"
}
    set_metricAction

    Change the latency chart to median, mean, or p95 and return the updated displayed results.

    View tool JSON
    {
  "name": "set_metric",
  "kind": "act",
  "impl": "imperative",
  "description": "Change the latency chart to median, mean, or p95 and return the updated displayed results.",
  "inputSchema": {
    "type": "object",
    "properties": {
      "metric": {
        "type": "string",
        "enum": [
          "median_ms",
          "mean_ms",
          "p95_ms"
        ]
      }
    },
    "required": [
      "metric"
    ],
    "additionalProperties": false
  },
  "page": "/"
}
    get_accuracyAnswer

    Read the selected model’s classification accuracy, per-class scores, and every incorrect prediction against the dataset labels.

    View tool JSON
    {
  "name": "get_accuracy",
  "kind": "answer",
  "impl": "imperative",
  "description": "Read the selected model’s classification accuracy, per-class scores, and every incorrect prediction against the dataset labels.",
  "inputSchema": {
    "type": "object",
    "properties": {},
    "required": [],
    "additionalProperties": false
  },
  "page": "/"
}
    select_accuracy_modelAction

    Choose a model in the selected experiment and return the accuracy and mistakes now displayed on the page.

    View tool JSON
    {
  "name": "select_accuracy_model",
  "kind": "act",
  "impl": "imperative",
  "description": "Choose a model in the selected experiment and return the accuracy and mistakes now displayed on the page.",
  "inputSchema": {
    "type": "object",
    "properties": {
      "model_name": {
        "type": "string"
      }
    },
    "required": [
      "model_name"
    ],
    "additionalProperties": false
  },
  "page": "/"
}

    page: Test sets

    describeAnswer

    Describe the test-sets page and the decision test sets it shows.

    View tool JSON
    {
  "name": "describe",
  "kind": "answer",
  "impl": "imperative",
  "description": "Describe the test-sets page and the decision test sets it shows.",
  "inputSchema": {
    "type": "object",
    "properties": {},
    "required": [],
    "additionalProperties": false
  },
  "page": "/test-sets.html"
}
    list_test_setsAnswer

    List the published test sets with their question type, labels and case count.

    View tool JSON
    {
  "name": "list_test_sets",
  "kind": "answer",
  "impl": "imperative",
  "description": "List the published test sets with their question type, labels and case count.",
  "inputSchema": {
    "type": "object",
    "properties": {},
    "required": [],
    "additionalProperties": false
  },
  "page": "/test-sets.html"
}
    get_test_setAnswer

    Read one test set's instructions, labels, criteria, cases and expected answers.

    View tool JSON
    {
  "name": "get_test_set",
  "kind": "answer",
  "impl": "imperative",
  "description": "Read one test set's instructions, labels, criteria, cases and expected answers.",
  "inputSchema": {
    "type": "object",
    "properties": {
      "set_id": {
        "type": "string"
      }
    },
    "required": [
      "set_id"
    ],
    "additionalProperties": false
  },
  "page": "/test-sets.html"
}