---
title: "List Benchmark Spec Tasks"
method: GET
path: "/api/v1/benchmarks/{bench_id}/tasks"
tags: ["benchmarks"]
---

# List Benchmark Spec Tasks

`GET /api/v1/benchmarks/{bench_id}/tasks`

## Path parameters

- `bench_id` string, required

## Query parameters

- `cursor` string, nullable
- `limit` integer
- `sort` string, nullable
- `order` 'asc' | 'desc'
- `search` string, nullable

## Response `200`

Successful Response

- PaginatedResponseBenchmarkSpecTask
  - `items` BenchmarkSpecTask[], required
    - `task_id` string, required
    - `label` string, nullable
    - `split` 'train' | 'test'
    - `input_message` string, nullable
    - `task_category` BenchmarkTaskCategory
      - `task_category_id` string, required
      - `label` string, required
    - `runtime_id` string, nullable
    - `run_command` string, nullable — For SDK evaluation and training, the command to run your agent in the sandbox, e.g. `python /app/agent.py`. Your script must call the model, run any tools, log a reward, and finalize the trajectory before exiting.
    - `build_status` string, nullable
    - `env_vars` object
  - `next_cursor` string, nullable
  - `has_more` boolean, required

## Changes

- **2026-09-24** `4087cc7a74aa` — 1 info
  - endpoint added

[Change history](https://skmtc.dev/trajectory/apis/trajectory-api/changes/api/v1/benchmarks/:bench_id/tasks/get.md)

---

[API](https://skmtc.dev/trajectory/apis/trajectory-api.md) · [All operations](https://skmtc.dev/trajectory/apis/trajectory-api/llms.txt) · [OpenAPI document](https://skmtc.dev/trajectory/apis/trajectory-api/revisions/8331f8435ce8?raw)