{"ok":true,"site":{"host":"jev-bench.cocode.dk","url":"https://jev-bench.cocode.dk/","type":"live","desc":"Jev Bench is an open classifier workbench: compare API latency and label accuracy with repeatable datasets, named models, and downloadable results.","tools":[{"name":"describe","kind":"answer","impl":"imperative","description":"Describe the Jev Bench results page, its selected experiment, and available controls.","annotations":{"readOnlyHint":true,"consequentialHint":false,"untrustedContentHint":false},"inputSchema":{"type":"object","properties":{},"required":[],"additionalProperties":false},"hasHandler":true,"hasExecute":true,"__source":"spec","executable":true,"handlerField":"execute","page":"/","pages":["/"]},{"name":"list_runs","kind":"answer","impl":"imperative","description":"List the published classification experiments available in the page's experiment selector.","annotations":{"readOnlyHint":true,"consequentialHint":false,"untrustedContentHint":false},"inputSchema":{"type":"object","properties":{},"required":[],"additionalProperties":false},"hasHandler":true,"hasExecute":true,"__source":"spec","executable":true,"handlerField":"execute","page":"/","pages":["/"]},{"name":"get_results","kind":"answer","impl":"imperative","description":"Read the selected experiment's latency, accuracy, error counts, and returned model names.","annotations":{"readOnlyHint":true,"consequentialHint":false,"untrustedContentHint":true},"inputSchema":{"type":"object","properties":{},"required":[],"additionalProperties":false},"hasHandler":true,"hasExecute":true,"__source":"spec","executable":true,"handlerField":"execute","page":"/","pages":["/"]},{"name":"select_run","kind":"act","impl":"imperative","description":"Select a published experiment and return the results now displayed on the page.","annotations":{"readOnlyHint":false,"consequentialHint":false,"untrustedContentHint":true},"inputSchema":{"type":"object","properties":{"run_id":{"type":"string"}},"required":["run_id"],"additionalProperties":false},"hasHandler":true,"hasExecute":true,"__source":"spec","executable":true,"handlerField":"execute","page":"/","pages":["/"]},{"name":"set_metric","kind":"act","impl":"imperative","description":"Change the latency chart to median, mean, or p95 and return the updated displayed results.","annotations":{"readOnlyHint":false,"consequentialHint":false,"untrustedContentHint":true},"inputSchema":{"type":"object","properties":{"metric":{"type":"string","enum":["median_ms","mean_ms","p95_ms"]}},"required":["metric"],"additionalProperties":false},"hasHandler":true,"hasExecute":true,"__source":"spec","executable":true,"handlerField":"execute","page":"/","pages":["/"]},{"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.","annotations":{"readOnlyHint":true,"consequentialHint":false,"untrustedContentHint":true},"inputSchema":{"type":"object","properties":{},"required":[],"additionalProperties":false},"hasHandler":true,"hasExecute":true,"__source":"spec","executable":true,"handlerField":"execute","page":"/","pages":["/"]},{"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.","annotations":{"readOnlyHint":false,"consequentialHint":false,"untrustedContentHint":true},"inputSchema":{"type":"object","properties":{"model_name":{"type":"string"}},"required":["model_name"],"additionalProperties":false},"hasHandler":true,"hasExecute":true,"__source":"spec","executable":true,"handlerField":"execute","page":"/","pages":["/"]},{"name":"describe","kind":"answer","impl":"imperative","description":"Describe the test-sets page and the decision test sets it shows.","annotations":{"readOnlyHint":true,"consequentialHint":false,"untrustedContentHint":false},"inputSchema":{"type":"object","properties":{},"required":[],"additionalProperties":false},"hasHandler":true,"hasExecute":true,"__source":"spec","executable":true,"handlerField":"execute","page":"/test-sets.html","pages":["/test-sets.html"]},{"name":"list_test_sets","kind":"answer","impl":"imperative","description":"List the published test sets with their question type, labels and case count.","annotations":{"readOnlyHint":true,"consequentialHint":false,"untrustedContentHint":false},"inputSchema":{"type":"object","properties":{},"required":[],"additionalProperties":false},"hasHandler":true,"hasExecute":true,"__source":"spec","executable":true,"handlerField":"execute","page":"/test-sets.html","pages":["/test-sets.html"]},{"name":"get_test_set","kind":"answer","impl":"imperative","description":"Read one test set's instructions, labels, criteria, cases and expected answers.","annotations":{"readOnlyHint":true,"consequentialHint":false,"untrustedContentHint":true},"inputSchema":{"type":"object","properties":{"set_id":{"type":"string"}},"required":["set_id"],"additionalProperties":false},"hasHandler":true,"hasExecute":true,"__source":"spec","executable":true,"handlerField":"execute","page":"/test-sets.html","pages":["/test-sets.html"]}],"category":"AI & Agents","favicon":"/favicons/jev-bench.cocode.dk.png","apiSurface":"spec","toolCount":10}}