GET/api/v1/evals/{runId}/results

Get per-case results for an eval run

Returns the EvalCaseResult[] array for a finished run — one entry per (test case × scorer) pair, with score, reason, latency, and any error. Streamable for very long runs via the `?stream=ndjson` query param.

Authentication

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

Parameters

stream in query

Stream results as newline-delimited JSON.

string

Response

200 example

[
  {
    "input": "string",
    "expectedOutput": "string",
    "actualOutput": "string",
    "score": 0,
    "passed": false,
    "latency": 0,
    "tokenUsage": {},
    "scorerResults": {}
  }
]

All status codes

200Per-case results.
400(no description)
401(no description)
404(no description)
429(no description)

Code samples

cURL

curl -X GET \
  https://evalguard.ai/api/v1/evals/{runId}/results \
  -H "Authorization: Bearer $EVALGUARD_API_KEY" \

TypeScript

import { EvalGuard } from "@evalguard/sdk";

const client = new EvalGuard({ apiKey: process.env.EVALGUARD_API_KEY });

const response = await client.request({
  method: "GET",
  path: "/api/v1/evals/{runId}/results",
});
console.log(response);

Python

from evalguard import EvalGuard
import os

client = EvalGuard(api_key=os.environ["EVALGUARD_API_KEY"])

response = client.request(method="GET", path="/api/v1/evals/{runId}/results")
print(response)

Go

package main

import (
	"context"
	"fmt"
	"os"

	"github.com/evalguard/evalguard-go"
)

func main() {
	client := evalguard.NewClient(os.Getenv("EVALGUARD_API_KEY"))
	resp, err := client.Request(context.Background(), "GET", "/api/v1/evals/{runId}/results", nil)
	if err != nil { panic(err) }
	fmt.Println(resp)
}

Errors

400401404429

Other Evals endpoints