Skip to content

parseEvalResults

reference
1 min readUpdated

Kind: Function

Source: atloria-monorepo/libs/agent-core/src/benchmark/swebench-evaluator.ts

Parse evaluation results from the harness output.

The harness writes results to {run_id}/results.json with format:

json
{
  "instance_id": {
    "resolved": true|false,
    "tests_status": { "FAIL_TO_PASS": {...}, "PASS_TO_PASS": {...} }
  }
}

Signature

ts
function parseEvalResults(resultsDir: string): EvalResult[]

Parameters

NameType
resultsDirstring

Returns: EvalResult[]

Was this page helpful?

Download as PDF