{"slug":"aialign-halowerk-com-v1-capability-eval-11488f","title":"Computes weighted pass rates and weighted scores from caller-labeled test outcom","host":"aialign.halowerk.com","method":"POST","resource":"https://aialign.halowerk.com/v1/capability-eval","category":"other","description":"Computes weighted pass rates and weighted scores from caller-labeled test outcomes, with deterministic category summaries. It does not run tests, validate labels, measure untested capabilities or establish deployment safety; the result is only as representative as the supplied evaluation set.","price_listed":0.003,"price_asked":0.003,"state":"answering","state_label":"Answering","checks_7d":1,"answered_7d":1,"latency_ms_median":951,"reported_calls_30d":1,"reported_payers_30d":1,"networks":["eip155:8453"],"badge":"unverified","paid_checks_7d":0,"paid_ok_7d":0,"example_input":{"body":{"test_cases":[{"case_id":"math-1","category":"reasoning","passed":true,"score":0.92,"weight":1},{"case_id":"math-2","category":"reasoning","passed":false,"score":0.41,"weight":1},{"case_id":"tool-1","category":"tool-use","passed":true,"score":0.88,"weight":2}]},"bodyType":"json","method":"POST","type":"http"},"output_schema":{"$schema":"https://json-schema.org/draft/2020-12/schema","properties":{"input":{"additionalProperties":false,"properties":{"body":{"additionalProperties":false,"properties":{"test_cases":{"items":{"additionalProperties":false,"properties":{"case_id":{"maxLength":128,"minLength":1,"type":"string"},"category":{"maxLength":128,"minLength":1,"type":"string"},"passed":{"type":"boolean"},"score":{"maximum":1,"minimum":0,"type":"number"},"weight":{"maximum":1000000,"minimum":1e-06,"type":"number"}},"required":["case_id","category","passed","score","weight"],"type":"object"},"maxItems":100000,"minItems":1,"type":"array"}},"required":["test_cases"],"type":"object"},"bodyType":{"enum":["json","form-data","text"],"type":"string"},"method":{"enum":["POST","PUT","PATCH"],"type":"string"},"type":{"const":"http","type":"string"}},"required":["type","method","bodyType","body"],"type":"object"}},"required":["input"],"type":"object"},"history":[{"day":"2026-09-24","reachable":true,"status":402,"valid_402":true,"asked_usdc":0.003,"price_match":true,"latency_ms":951,"error":null}],"description_full":"Computes weighted pass rates and weighted scores from caller-labeled test outcomes, with deterministic category summaries. It does not run tests, validate labels, measure untested capabilities or establish deployment safety; the result is only as representative as the supplied evaluation set.","last_updated":"2026-09-24T14:11:08.618Z","schemes":["exact"]}