Results And Reports

Use these calls after a benchmark job or run completes. Return ids, metric highlights, caveats, and report URLs rather than large raw payloads.

Set these environment variables for the examples:

export METRUM_API_URL="https://api.<control-plane-domain>"
export METRUM_WEBUI_URL="https://<control-plane-host-or-dns>"
export METRUM_JWT_TOKEN="<12-hour-db-minted-postgrest-jwt>"

Benchmark Results

Returns benchmark rows with model, framework, hardware, throughput, and latency.

curl -fsS "$METRUM_API_URL/v_benchmark_results?org_id=eq.$METRUM_ORG_ID&project_name=eq.deepseek-qwen15b-rtxpro6000-smoke&limit=50" \
  -H "X-Org-Id: $METRUM_ORG_ID" \
  -H "Authorization: Bearer $METRUM_JWT_TOKEN" | jq

Query parameters:

Name	Required	Description
project_name	No	Use eq.<name> to filter by project name.
model_code	No	Use eq.<code> to filter by model code.
framework_code	No	Use eq.<code> to filter by framework code.
limit	No	Maximum rows to return.

Telemetry Summary

Returns telemetry for either a run or a job.

curl -fsS -X POST "$METRUM_API_URL/rpc/get_telemetry_summary_for_run" \
  -H "Authorization: Bearer $METRUM_JWT_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"p_run_id":1}' | jq

curl -fsS -X POST "$METRUM_API_URL/rpc/get_telemetry_summary_for_job" \
  -H "Authorization: Bearer $METRUM_JWT_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"p_job_id":123}' | jq

Parameters:

RPC	Parameter	Required	Description
get_telemetry_summary_for_run	p_run_id	Yes	Run id.
get_telemetry_summary_for_job	p_job_id	Yes	Job id.

Job Outputs

Returns metrumbench-llm output metrics for a job.

curl -fsS "$METRUM_API_URL/v_metrumbench_llm_outputs?job_id=eq.123&limit=100" \
  -H "Authorization: Bearer $METRUM_JWT_TOKEN" | jq

Query parameters:

Name	Required	Description
job_id	No	Use eq.<id> to filter by job.
limit	No	Maximum rows to return.

Run Cost Summary

Returns cost summaries for recent runs.

curl -fsS "$METRUM_API_URL/v_run_cost_summary?limit=50" \
  -H "Authorization: Bearer $METRUM_JWT_TOKEN" | jq

Query parameters:

Name	Required	Description
limit	No	Maximum rows to return.

Reports

Fetch report output and downloadable artifacts from WebUI.

curl -fsS -X POST "$METRUM_WEBUI_URL/api/ai-eval" \
  -H "Authorization: Bearer $METRUM_JWT_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"run_id":1}' | jq

curl -fsS -OJ "$METRUM_WEBUI_URL/api/run-report/1" \
  -H "Authorization: Bearer $METRUM_JWT_TOKEN"

curl -fsS -OJ "$METRUM_WEBUI_URL/api/project-run-report/1" \
  -H "Authorization: Bearer $METRUM_JWT_TOKEN"

Report URLs:

URL	Description
/api/benchmark-report/:runId	Benchmark run HTML report.
/api/benchmark-report/:runId?ai=1	Benchmark run HTML report with AI assistance.
/api/run-report/:runId	Benchmark run spreadsheet export.
/api/project-report/:projectId	Project-level HTML report.
/api/project-report/:projectId?ai=1	Project-level HTML report with AI assistance.
/api/project-run-report/:projectId	Project-level spreadsheet export.