ListEvalSuiteLeaderboardRunsData

Example Usage

import { ListEvalSuiteLeaderboardRunsData } from "@meetkai/mka1/models/operations";

let value: ListEvalSuiteLeaderboardRunsData = {
  id: "<id>",
  object: "eval.run",
  suiteId: "<id>",
  suiteVersion: 666,
  suiteVersionId: "<id>",
  orgId: "<id>",
  teamId: "<id>",
  status: "completed",
  models: [
    "<value 1>",
  ],
  taskIds: [
    "<value 1>",
    "<value 2>",
    "<value 3>",
  ],
  judgeModel: "<value>",
  embeddingModel: "<value>",
  generation: {},
  requestCounts: {
    total: 843051,
    completed: 4960,
    failed: 868344,
  },
  metrics: {
    "key": "<value>",
    "key1": "<value>",
  },
  error: null,
  artifactFileIds: [
    "<value 1>",
  ],
  metadata: {
    "key": "<value>",
  },
  agentName: "<value>",
  agentVersion: "<value>",
  agentEffort: "<value>",
  costUsd: 2127.7,
  createdAt: 73112,
  startedAt: 456398,
  completedAt: 38270,
  cancelledAt: 40283,
  failedAt: null,
};

Fields

Field	Type	Required	Description
id	string	✔️	N/A
object	"eval.run"	✔️	N/A
suiteId	string	✔️	N/A
suiteVersion	number	✔️	N/A
suiteVersionId	string	✔️	N/A
orgId	string	✔️	The org that owns this run.
teamId	string	✔️	The team that owns this run.
status	components.EvalRunStatus	✔️	N/A
models	string[]	✔️	N/A
taskIds	string[]	✔️	N/A
judgeModel	string	✔️	N/A
embeddingModel	string	✔️	N/A
generation	operations.ListEvalSuiteLeaderboardRunsGeneration	✔️	N/A
requestCounts	operations.ListEvalSuiteLeaderboardRunsRequestCounts	✔️	N/A
metrics	Record<string, any>	✔️	N/A
error	Record<string, any>	✔️	N/A
artifactFileIds	string[]	✔️	N/A
metadata	Record<string, string>	✔️	N/A
agentName	string	✔️	Coding-agent harness that produced this run (e.g. omp, claude-code). Null for every non-harness eval kind — a null here is not a missing value, it means the run is not an agent run.
agentVersion	string	✔️	Version of agent_name, as the harness reported it. Null when agent_name is.
agentEffort	string	✔️	Reasoning-effort setting the agent ran at (e.g. medium, xhigh). Part of the leaderboard's row identity: the same agent and model at two efforts are two rows, not one. Null when agent_name is.
costUsd	number	✔️	Total spend for the run in USD. Null when the harness did not report cost.
createdAt	number	✔️	N/A
startedAt	number	✔️	N/A
completedAt	number	✔️	N/A
cancelledAt	number	✔️	N/A
failedAt	number	✔️	N/A