Skip to main content
POST
Launch a benchmark run

Authorizations

Authorization
string
header
required

Platform API token created under Profile Settings > Platform API tokens. Scopes are fixed at creation.

Body

application/json
competition_id
integer
required
model_id
integer

Platform model id (integer, preferred). Get it from the model catalogue; an already-running model is benchmarked against its live endpoint, no second deploy.

model
string

Catalogue model id (24-hex), a numeric platform id, or a model name (display or litellm). Names are resolved server-side against the catalogue, preferring a running instance; an unknown name is passed through and will fail the run, so prefer ids when scripting.

phase_id
integer

Optional phase override; defaults to the current phase

model_source
enum<string>
Available options:
platform,
external,
huggingface
env_vars
object

Extra env for the run container

temperature
number
max_tokens
integer
top_p
number

Response

Run queued

submission_id
integer
submission_status
string
resolved_model
object

How the model was resolved (model name, endpoint)

competition_id
integer
phase_id
integer
poll_path
string

GET this path for the full run record

run_status_path
string

GET this path to follow the run: state, score and link in one small answer

run_path
string | null

Web app path of the run page

Last modified on September 11, 2026