Skip to main content
The Model Router scores every candidate model on a weighted set of benchmarks, and the weights depend on the kind of task. This page lists the 27 task types the router classifies into, the eight families they belong to, and the benchmarks behind each one. Use it to choose a task_type to fix in a request, or to understand why the router picked a model. The tables below are the response of GET /v1/router/task-types with benchmarks as of 2026-09-24. The benchmark values and weights are refreshed with the catalog; read the endpoint for the current set, and benchmarks_as_of in any selection for the snapshot it used.

Read the task types

The response has benchmarks_as_of, families, and one entry per task type:

All task types

Benchmarks are listed by weight, largest first. Weights are rounded to two decimals.

Coding

Math

Science

Knowledge

Documents

Writing

Agents

Vision

Policies and task types

Every policy starts from the same classification. They differ in how they use it: Fix the task type when you already know it: "task_type": "translation" skips the task-type classification. Difficulty and facets are still classified, and classification.task_type.fixed is true. domain does the same with the coarse vocabulary and routes as that domain’s default task type; task_type wins when you send both. An id that is not in the list is 400 invalid_body.