Skip to content
GET/api/v1/evals/compare

Compare two eval runs

Side-by-side comparison of two eval runs, matching cases by input text. Returns regressions, improvements, and per-case diffs. Cross-tenant defense: projectId is REQUIRED and both runs must belong to it (404 otherwise).

Authentication

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

Parameters

runA in queryrequired

First eval run ID.

string
runB in queryrequired

Second eval run ID.

string
projectId in queryrequired

Project that owns both runs. Required (cross-tenant defense).

string

Response

200 example

{
  "success": true
}

All status codes

200Comparison result with run_a/run_b summaries, score_diff, regressions, improvements, unchanged, and per-case cases[].
400(no description)
401(no description)
404(no description)
429(no description)

Code samples

cURL

curl -X GET \
  https://evalguard.ai/api/v1/evals/compare \
  -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/compare",
});
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/compare")
print(response)

Go

package main

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

func main() {
	req, _ := http.NewRequestWithContext(context.Background(), "GET", "https://evalguard.ai/api/v1/evals/compare", 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

400401404429

Other Evals endpoints