---
title: "Start Eval Route"
method: POST
path: "/api/v1/eval/{bench_id}/start"
tags: ["eval"]
---

# Start Eval Route

`POST /api/v1/eval/{bench_id}/start`

## Path parameters

- `bench_id` string, required

## Request body

- StartEvalRequest
  - `model_slug` 'Qwen/Qwen3.5-4B' | 'Qwen/Qwen3.5-397B-A17B' | 'Qwen/Qwen3.6-35B-A3B' | 'nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16' | 'nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16' | 'nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16' | 'openai/gpt-5-mini' | 'openai/gpt-5.4-mini' | 'openai/gpt-5.5' | 'anthropic/claude-sonnet-4.6' | 'google/gemini-3.1-pro-preview', required
  - `display_name` string, nullable — User-facing name for the evaluation run.
  - `checkpoint_id` string, nullable — When set, evaluate this committed training checkpoint instead of the base model.

## Response `202`

Successful Response

- StartEvalResponse
  - `bench_id` string, required — Benchmark evaluated by this run.
  - `eval_run_id` string, required — Evaluation run created for this request.
  - `pipeline_run_id` string, required — Pipeline run executing the evaluation.
  - `display_name` string, nullable, required — User-facing name for the evaluation run.
  - `execution_id` string, required — Flyte execution launched for the evaluation.
  - `pipeline_name` string, required — Pipeline configuration used by the evaluation.
  - `experiment_name` string, required — Experiment name assigned to the evaluation.

---

[API](https://skmtc.dev/trajectory/apis/trajectory-api.md) · [All operations](https://skmtc.dev/trajectory/apis/trajectory-api/llms.txt) · [OpenAPI document](https://skmtc-service-production.skmtc.workers.dev/v1/apis/trajectory/trajectory-api/revisions/d930b23b9602/schema)