benchmark_model
modelid, providerid?, taskcategories?
How to use it
benchmark_model is exposed by the Locallama MCP MCP server. Add the server to your MCP client (Claude Desktop, Cursor, Windsurf and others), and the benchmark_model tool becomes available to the model automatically. See the full listing for setup details and every tool this server provides.
FULL LOCALLAMA MCP LISTINGOther tools in Locallama MCP (17)
tasks[], runspertask?, parallel?, maxparalleltasks?
taskid, task, contextlength, expectedoutputlength?, complexity?, localmodel?, paidmodel?, runspertask?
tasks[], runspertask?, parallel?, maxparalleltasks?
jobid
taskid
—
—
contextlength, expectedoutputlength?, model?
—
taskid
task, contextlength, expectedoutputlength?, complexity?, priority?
—
directories[], excludepatterns?, chunksize?, forcereindex?, bm25options?
query, limit?
task, contextlength, expectedoutputlength?, complexity?, priority?, preemptive?
modelid, systemprompt, userprompt, usechat, assistantprompt?, successrate?, qualityscore?
—