Skip to content
GET/api/v1/scorers/accuracy

Measured scorer-vs-ground-truth agreement

Publishes MEASURED agreement between EvalGuard's own scorers and committed labelled sets — the answer to "how do you know your judge is right?". Every number is computed at request time from the scorer registry and the committed labelled sets; nothing is hardcoded. The response deliberately includes the scorers that CANNOT be measured honestly, under `unmeasured` — a credibility endpoint that hid its own coverage gap would defeat its purpose. `labelledSets` carries set-level provenance so any number can be traced back to the bytes it came from. Deterministic and offline: no model calls and no egress. Computed once per process and memoised; a failed computation is not cached.

Authentication

Send Authorization: Bearer YOUR_API_KEY on every request. Generate API keys at /dashboard/settings/api-keys.

Parameters

scorer in query

Return only results for this scorer id. 404 SCORER_UNMEASURED when the scorer is registered but no labelled set covers it yet — distinct from 404 NOT_FOUND for an unknown id.

string
set in query

Return only results from this labelled-set id. 404 NOT_FOUND if unknown, or if the set does not measure the requested scorer.

string
view in query

`full` returns results + unmeasured + totals + disclaimers + labelledSets; `rows` returns the compact table shape. Any other value is 400 INVALID_VIEW.

string

Response

200 example

{
  "success": true
}

All status codes

200Agreement report. `view=full`: `{ results, unmeasured, totals, disclaimers, labelledSets }`. `view=rows`: `{ rows, totals, disclaimers }`.
400(no description)
401(no description)
403Forbidden — the credential is valid but lacks the API-key scope, member role, or plan entitlement this operation requires.
404(no description)
429(no description)
500Internal Server Error — an unhandled error was converted to the standard error envelope (INTERNAL_ERROR).

Code samples

cURL

curl -X GET \
  https://evalguard.ai/api/v1/scorers/accuracy \
  -H "Authorization: Bearer $EVALGUARD_API_KEY"

TypeScript

// The TypeScript SDK (@evalguard/sdk) exposes TYPED methods — runEval,
// getEval, runSecurityScan, checkFirewall, … — not a generic request().
// For an arbitrary endpoint, call it directly:

const res = await fetch("https://evalguard.ai/api/v1/scorers/accuracy", {
  method: "GET",
  headers: { Authorization: `Bearer ${process.env.EVALGUARD_API_KEY}` },
});
console.log(res.status, await res.json());

Python

# The Python SDK (pip install evalguardai) exposes TYPED methods on
# EvalGuardClient — run_eval, get_eval, … — not a generic request().
# For an arbitrary endpoint, call it directly:

import os
import requests

headers = {"Authorization": f"Bearer {os.environ['EVALGUARD_API_KEY']}"}

response = requests.request("GET", "https://evalguard.ai/api/v1/scorers/accuracy", headers=headers)
print(response.status_code, response.json())

Go

package main

import (
	"context"
	"fmt"
	"net/http"
	"os"
)

func main() {
	req, _ := http.NewRequestWithContext(context.Background(), "GET", "https://evalguard.ai/api/v1/scorers/accuracy", nil)
	req.Header.Set("Authorization", "Bearer "+os.Getenv("EVALGUARD_API_KEY"))
	resp, err := http.DefaultClient.Do(req)
	if err != nil { panic(err) }
	defer resp.Body.Close()
	fmt.Println(resp.Status)
}

Errors

400401403404429500

Other Evals endpoints