For AI agents: a documentation index is available at the root level at /llms.txt and /llms-full.txt. Append /llms.txt to any URL for a page-level index, or .md for the markdown version of any page.
Dashboard
User GuideDeveloper GuidesAPI Reference
User GuideDeveloper GuidesAPI Reference
    • Overview
  • Runtype API
      • POSTAnalyze step results
      • GETList eval batches
      • POSTCompare evals
      • POSTCompare record across evals
      • GETGet eval group
      • STREAMStream eval execution
      • POSTSubmit eval
      • GETGet eval results
Dashboard
LogoLogo
Runtype APIEvals

Get eval results

GET
/v1/eval/:id/results
GET
/v1/eval/:id/results
$curl https://api.runtype.com/v1/eval/id/results \
>     -H "Authorization: <apiKey>" \
>     -H "Content-Type: application/json"
1{
2  "batchExecutionId": "b7f3c9d2-4a1e-4f6a-9c3e-2d5a7b8e9f01",
3  "failedRecords": 2,
4  "flowId": "flow-9a8b7c6d",
5  "processedRecords": 50,
6  "resultsByRecord": {
7    "record-001": [
8      {
9        "completionTokens": 10,
10        "durationMs": 120,
11        "errorMessage": null,
12        "errorStack": null,
13        "executedAt": "2024-06-10T16:40:00Z",
14        "executionSessionId": "sess-5678efgh",
15        "messageHistory": [
16          {
17            "role": "user",
18            "content": "I want to check my order status."
19          }
20        ],
21        "modelUsed": "gpt-4-chat",
22        "output": "Order Status Inquiry",
23        "promptTokens": 15,
24        "reasoningContent": "The query explicitly asks about order status, indicating intent to check order progress.",
25        "reasoningTokens": 20,
26        "recordName": "Customer Query #001",
27        "resolvedPrompt": "Classify the intent of the customer query: 'I want to check my order status.'",
28        "retryCount": 0,
29        "stepId": "step-01",
30        "stepName": "Intent Classification",
31        "stepResultId": "stepres-1234abcd",
32        "stepType": "classification",
33        "toolCalls": [
34          {
35            "errorMessage": null,
36            "executedAt": "2024-06-10T16:40:00Z",
37            "executionTimeMs": 100,
38            "model": "intent-model-v2",
39            "status": "success",
40            "toolDescription": "Classifies user intents from text input",
41            "toolExecutionId": "toolexec-7890ijkl",
42            "toolId": "tool-nlp-01",
43            "toolName": "IntentClassifier",
44            "inputParameters": {
45              "text": "I want to check my order status."
46            },
47            "outputResult": {
48              "intent": "Order Status Inquiry",
49              "confidence": 0.95
50            }
51          }
52        ],
53        "totalCost": 0.0025
54      }
55    ]
56  },
57  "startedAt": "2024-06-10T16:30:00Z",
58  "status": "completed",
59  "totalRecords": 50,
60  "completedAt": "2024-06-10T16:45:30Z",
61  "evalGroupId": "evalgroup-20240610",
62  "evalName": "Customer Support Chatbot Accuracy Test"
63}
Get detailed results for a specific eval batch including step results and tool calls.
Was this page helpful?
Previous

List feedback with filters

Next
Built with

Authentication

AuthorizationBearer
API key or Clerk session token

Path parameters

idstringRequired
Batch execution ID

Response

Eval results returned
batchExecutionIdstring
failedRecordsinteger
flowIdstring or null
processedRecordsinteger
resultsByRecordmap from strings to lists of objects
startedAtstring
statusstring
totalRecordsinteger
completedAtstring
evalConfigany
evalGroupIdstring
evalNamestring

Errors

401
Unauthorized Error
404
Not Found Error
500
Internal Server Error