Create Evaluation
curl --request POST \
--url https://api.primeintellect.ai/api/v1/evaluations/ \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"name": "<string>",
"team_id": "<string>",
"environments": [
{
"id": "<string>",
"version_id": "<string>"
}
],
"suite_id": "<string>",
"run_id": "<string>",
"is_hosted": false,
"inference_model": "<string>",
"eval_config": {
"num_examples": 4503599627370495,
"rollouts_per_example": 1024,
"env_args": {},
"allow_sandbox_access": true,
"allow_instances_access": false,
"allow_tunnel_access": true,
"timeout_minutes": 123,
"custom_secrets": {},
"sampling_args": {},
"max_concurrent": 4503599627370496,
"auto_max_concurrent": false,
"max_retries": 4503599627370495,
"state_columns": [
"<string>"
],
"independent_scoring": false,
"verbose": false,
"headers": [
"<string>"
],
"extra_env_kwargs": {},
"api_client_type": "<string>",
"api_base_url": "<string>",
"api_key_var": "<string>"
},
"model_name": "<string>",
"dataset": "<string>",
"framework": "<string>",
"task_type": "<string>",
"description": "<string>",
"tags": [],
"metadata": {},
"metrics": {},
"is_public": false,
"show_on_leaderboard": false
}
'import requests
url = "https://api.primeintellect.ai/api/v1/evaluations/"
payload = {
"name": "<string>",
"team_id": "<string>",
"environments": [
{
"id": "<string>",
"version_id": "<string>"
}
],
"suite_id": "<string>",
"run_id": "<string>",
"is_hosted": False,
"inference_model": "<string>",
"eval_config": {
"num_examples": 4503599627370495,
"rollouts_per_example": 1024,
"env_args": {},
"allow_sandbox_access": True,
"allow_instances_access": False,
"allow_tunnel_access": True,
"timeout_minutes": 123,
"custom_secrets": {},
"sampling_args": {},
"max_concurrent": 4503599627370496,
"auto_max_concurrent": False,
"max_retries": 4503599627370495,
"state_columns": ["<string>"],
"independent_scoring": False,
"verbose": False,
"headers": ["<string>"],
"extra_env_kwargs": {},
"api_client_type": "<string>",
"api_base_url": "<string>",
"api_key_var": "<string>"
},
"model_name": "<string>",
"dataset": "<string>",
"framework": "<string>",
"task_type": "<string>",
"description": "<string>",
"tags": [],
"metadata": {},
"metrics": {},
"is_public": False,
"show_on_leaderboard": False
}
headers = {
"Authorization": "Bearer <token>",
"Content-Type": "application/json"
}
response = requests.post(url, json=payload, headers=headers)
print(response.text)const options = {
method: 'POST',
headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
body: JSON.stringify({
name: '<string>',
team_id: '<string>',
environments: [{id: '<string>', version_id: '<string>'}],
suite_id: '<string>',
run_id: '<string>',
is_hosted: false,
inference_model: '<string>',
eval_config: {
num_examples: 4503599627370495,
rollouts_per_example: 1024,
env_args: {},
allow_sandbox_access: true,
allow_instances_access: false,
allow_tunnel_access: true,
timeout_minutes: 123,
custom_secrets: {},
sampling_args: {},
max_concurrent: 4503599627370496,
auto_max_concurrent: false,
max_retries: 4503599627370495,
state_columns: ['<string>'],
independent_scoring: false,
verbose: false,
headers: ['<string>'],
extra_env_kwargs: {},
api_client_type: '<string>',
api_base_url: '<string>',
api_key_var: '<string>'
},
model_name: '<string>',
dataset: '<string>',
framework: '<string>',
task_type: '<string>',
description: '<string>',
tags: [],
metadata: {},
metrics: {},
is_public: false,
show_on_leaderboard: false
})
};
fetch('https://api.primeintellect.ai/api/v1/evaluations/', options)
.then(res => res.json())
.then(res => console.log(res))
.catch(err => console.error(err));<?php
$curl = curl_init();
curl_setopt_array($curl, [
CURLOPT_URL => "https://api.primeintellect.ai/api/v1/evaluations/",
CURLOPT_RETURNTRANSFER => true,
CURLOPT_ENCODING => "",
CURLOPT_MAXREDIRS => 10,
CURLOPT_TIMEOUT => 30,
CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
CURLOPT_CUSTOMREQUEST => "POST",
CURLOPT_POSTFIELDS => json_encode([
'name' => '<string>',
'team_id' => '<string>',
'environments' => [
[
'id' => '<string>',
'version_id' => '<string>'
]
],
'suite_id' => '<string>',
'run_id' => '<string>',
'is_hosted' => false,
'inference_model' => '<string>',
'eval_config' => [
'num_examples' => 4503599627370495,
'rollouts_per_example' => 1024,
'env_args' => [
],
'allow_sandbox_access' => true,
'allow_instances_access' => false,
'allow_tunnel_access' => true,
'timeout_minutes' => 123,
'custom_secrets' => [
],
'sampling_args' => [
],
'max_concurrent' => 4503599627370496,
'auto_max_concurrent' => false,
'max_retries' => 4503599627370495,
'state_columns' => [
'<string>'
],
'independent_scoring' => false,
'verbose' => false,
'headers' => [
'<string>'
],
'extra_env_kwargs' => [
],
'api_client_type' => '<string>',
'api_base_url' => '<string>',
'api_key_var' => '<string>'
],
'model_name' => '<string>',
'dataset' => '<string>',
'framework' => '<string>',
'task_type' => '<string>',
'description' => '<string>',
'tags' => [
],
'metadata' => [
],
'metrics' => [
],
'is_public' => false,
'show_on_leaderboard' => false
]),
CURLOPT_HTTPHEADER => [
"Authorization: Bearer <token>",
"Content-Type: application/json"
],
]);
$response = curl_exec($curl);
$err = curl_error($curl);
curl_close($curl);
if ($err) {
echo "cURL Error #:" . $err;
} else {
echo $response;
}package main
import (
"fmt"
"strings"
"net/http"
"io"
)
func main() {
url := "https://api.primeintellect.ai/api/v1/evaluations/"
payload := strings.NewReader("{\n \"name\": \"<string>\",\n \"team_id\": \"<string>\",\n \"environments\": [\n {\n \"id\": \"<string>\",\n \"version_id\": \"<string>\"\n }\n ],\n \"suite_id\": \"<string>\",\n \"run_id\": \"<string>\",\n \"is_hosted\": false,\n \"inference_model\": \"<string>\",\n \"eval_config\": {\n \"num_examples\": 4503599627370495,\n \"rollouts_per_example\": 1024,\n \"env_args\": {},\n \"allow_sandbox_access\": true,\n \"allow_instances_access\": false,\n \"allow_tunnel_access\": true,\n \"timeout_minutes\": 123,\n \"custom_secrets\": {},\n \"sampling_args\": {},\n \"max_concurrent\": 4503599627370496,\n \"auto_max_concurrent\": false,\n \"max_retries\": 4503599627370495,\n \"state_columns\": [\n \"<string>\"\n ],\n \"independent_scoring\": false,\n \"verbose\": false,\n \"headers\": [\n \"<string>\"\n ],\n \"extra_env_kwargs\": {},\n \"api_client_type\": \"<string>\",\n \"api_base_url\": \"<string>\",\n \"api_key_var\": \"<string>\"\n },\n \"model_name\": \"<string>\",\n \"dataset\": \"<string>\",\n \"framework\": \"<string>\",\n \"task_type\": \"<string>\",\n \"description\": \"<string>\",\n \"tags\": [],\n \"metadata\": {},\n \"metrics\": {},\n \"is_public\": false,\n \"show_on_leaderboard\": false\n}")
req, _ := http.NewRequest("POST", url, payload)
req.Header.Add("Authorization", "Bearer <token>")
req.Header.Add("Content-Type", "application/json")
res, _ := http.DefaultClient.Do(req)
defer res.Body.Close()
body, _ := io.ReadAll(res.Body)
fmt.Println(string(body))
}HttpResponse<String> response = Unirest.post("https://api.primeintellect.ai/api/v1/evaluations/")
.header("Authorization", "Bearer <token>")
.header("Content-Type", "application/json")
.body("{\n \"name\": \"<string>\",\n \"team_id\": \"<string>\",\n \"environments\": [\n {\n \"id\": \"<string>\",\n \"version_id\": \"<string>\"\n }\n ],\n \"suite_id\": \"<string>\",\n \"run_id\": \"<string>\",\n \"is_hosted\": false,\n \"inference_model\": \"<string>\",\n \"eval_config\": {\n \"num_examples\": 4503599627370495,\n \"rollouts_per_example\": 1024,\n \"env_args\": {},\n \"allow_sandbox_access\": true,\n \"allow_instances_access\": false,\n \"allow_tunnel_access\": true,\n \"timeout_minutes\": 123,\n \"custom_secrets\": {},\n \"sampling_args\": {},\n \"max_concurrent\": 4503599627370496,\n \"auto_max_concurrent\": false,\n \"max_retries\": 4503599627370495,\n \"state_columns\": [\n \"<string>\"\n ],\n \"independent_scoring\": false,\n \"verbose\": false,\n \"headers\": [\n \"<string>\"\n ],\n \"extra_env_kwargs\": {},\n \"api_client_type\": \"<string>\",\n \"api_base_url\": \"<string>\",\n \"api_key_var\": \"<string>\"\n },\n \"model_name\": \"<string>\",\n \"dataset\": \"<string>\",\n \"framework\": \"<string>\",\n \"task_type\": \"<string>\",\n \"description\": \"<string>\",\n \"tags\": [],\n \"metadata\": {},\n \"metrics\": {},\n \"is_public\": false,\n \"show_on_leaderboard\": false\n}")
.asString();require 'uri'
require 'net/http'
url = URI("https://api.primeintellect.ai/api/v1/evaluations/")
http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true
request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n \"name\": \"<string>\",\n \"team_id\": \"<string>\",\n \"environments\": [\n {\n \"id\": \"<string>\",\n \"version_id\": \"<string>\"\n }\n ],\n \"suite_id\": \"<string>\",\n \"run_id\": \"<string>\",\n \"is_hosted\": false,\n \"inference_model\": \"<string>\",\n \"eval_config\": {\n \"num_examples\": 4503599627370495,\n \"rollouts_per_example\": 1024,\n \"env_args\": {},\n \"allow_sandbox_access\": true,\n \"allow_instances_access\": false,\n \"allow_tunnel_access\": true,\n \"timeout_minutes\": 123,\n \"custom_secrets\": {},\n \"sampling_args\": {},\n \"max_concurrent\": 4503599627370496,\n \"auto_max_concurrent\": false,\n \"max_retries\": 4503599627370495,\n \"state_columns\": [\n \"<string>\"\n ],\n \"independent_scoring\": false,\n \"verbose\": false,\n \"headers\": [\n \"<string>\"\n ],\n \"extra_env_kwargs\": {},\n \"api_client_type\": \"<string>\",\n \"api_base_url\": \"<string>\",\n \"api_key_var\": \"<string>\"\n },\n \"model_name\": \"<string>\",\n \"dataset\": \"<string>\",\n \"framework\": \"<string>\",\n \"task_type\": \"<string>\",\n \"description\": \"<string>\",\n \"tags\": [],\n \"metadata\": {},\n \"metrics\": {},\n \"is_public\": false,\n \"show_on_leaderboard\": false\n}"
response = http.request(request)
puts response.read_body{
"evaluation_id": "<string>",
"name": "<string>",
"created_at": "2023-11-07T05:31:56Z",
"environment_ids": [
"<string>"
],
"suite_id": "<string>",
"run_id": "<string>",
"version_id": "<string>",
"viewer_url": "<string>"
}{
"errors": [
{
"param": "<string>",
"details": "<string>"
}
]
}evals
Create Evaluation
Create a new evaluation
This endpoint supports:
- Environment evaluations: Provide environments
- Prime RL evaluations: Provide run_id
- Suite evaluations: Provide suite_id
Ownership:
- If team_id is provided in request, the evaluation will be owned by the team
- Otherwise, the evaluation will be owned by the authenticated user
POST
/
api
/
v1
/
evaluations
/
Create Evaluation
curl --request POST \
--url https://api.primeintellect.ai/api/v1/evaluations/ \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"name": "<string>",
"team_id": "<string>",
"environments": [
{
"id": "<string>",
"version_id": "<string>"
}
],
"suite_id": "<string>",
"run_id": "<string>",
"is_hosted": false,
"inference_model": "<string>",
"eval_config": {
"num_examples": 4503599627370495,
"rollouts_per_example": 1024,
"env_args": {},
"allow_sandbox_access": true,
"allow_instances_access": false,
"allow_tunnel_access": true,
"timeout_minutes": 123,
"custom_secrets": {},
"sampling_args": {},
"max_concurrent": 4503599627370496,
"auto_max_concurrent": false,
"max_retries": 4503599627370495,
"state_columns": [
"<string>"
],
"independent_scoring": false,
"verbose": false,
"headers": [
"<string>"
],
"extra_env_kwargs": {},
"api_client_type": "<string>",
"api_base_url": "<string>",
"api_key_var": "<string>"
},
"model_name": "<string>",
"dataset": "<string>",
"framework": "<string>",
"task_type": "<string>",
"description": "<string>",
"tags": [],
"metadata": {},
"metrics": {},
"is_public": false,
"show_on_leaderboard": false
}
'import requests
url = "https://api.primeintellect.ai/api/v1/evaluations/"
payload = {
"name": "<string>",
"team_id": "<string>",
"environments": [
{
"id": "<string>",
"version_id": "<string>"
}
],
"suite_id": "<string>",
"run_id": "<string>",
"is_hosted": False,
"inference_model": "<string>",
"eval_config": {
"num_examples": 4503599627370495,
"rollouts_per_example": 1024,
"env_args": {},
"allow_sandbox_access": True,
"allow_instances_access": False,
"allow_tunnel_access": True,
"timeout_minutes": 123,
"custom_secrets": {},
"sampling_args": {},
"max_concurrent": 4503599627370496,
"auto_max_concurrent": False,
"max_retries": 4503599627370495,
"state_columns": ["<string>"],
"independent_scoring": False,
"verbose": False,
"headers": ["<string>"],
"extra_env_kwargs": {},
"api_client_type": "<string>",
"api_base_url": "<string>",
"api_key_var": "<string>"
},
"model_name": "<string>",
"dataset": "<string>",
"framework": "<string>",
"task_type": "<string>",
"description": "<string>",
"tags": [],
"metadata": {},
"metrics": {},
"is_public": False,
"show_on_leaderboard": False
}
headers = {
"Authorization": "Bearer <token>",
"Content-Type": "application/json"
}
response = requests.post(url, json=payload, headers=headers)
print(response.text)const options = {
method: 'POST',
headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
body: JSON.stringify({
name: '<string>',
team_id: '<string>',
environments: [{id: '<string>', version_id: '<string>'}],
suite_id: '<string>',
run_id: '<string>',
is_hosted: false,
inference_model: '<string>',
eval_config: {
num_examples: 4503599627370495,
rollouts_per_example: 1024,
env_args: {},
allow_sandbox_access: true,
allow_instances_access: false,
allow_tunnel_access: true,
timeout_minutes: 123,
custom_secrets: {},
sampling_args: {},
max_concurrent: 4503599627370496,
auto_max_concurrent: false,
max_retries: 4503599627370495,
state_columns: ['<string>'],
independent_scoring: false,
verbose: false,
headers: ['<string>'],
extra_env_kwargs: {},
api_client_type: '<string>',
api_base_url: '<string>',
api_key_var: '<string>'
},
model_name: '<string>',
dataset: '<string>',
framework: '<string>',
task_type: '<string>',
description: '<string>',
tags: [],
metadata: {},
metrics: {},
is_public: false,
show_on_leaderboard: false
})
};
fetch('https://api.primeintellect.ai/api/v1/evaluations/', options)
.then(res => res.json())
.then(res => console.log(res))
.catch(err => console.error(err));<?php
$curl = curl_init();
curl_setopt_array($curl, [
CURLOPT_URL => "https://api.primeintellect.ai/api/v1/evaluations/",
CURLOPT_RETURNTRANSFER => true,
CURLOPT_ENCODING => "",
CURLOPT_MAXREDIRS => 10,
CURLOPT_TIMEOUT => 30,
CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
CURLOPT_CUSTOMREQUEST => "POST",
CURLOPT_POSTFIELDS => json_encode([
'name' => '<string>',
'team_id' => '<string>',
'environments' => [
[
'id' => '<string>',
'version_id' => '<string>'
]
],
'suite_id' => '<string>',
'run_id' => '<string>',
'is_hosted' => false,
'inference_model' => '<string>',
'eval_config' => [
'num_examples' => 4503599627370495,
'rollouts_per_example' => 1024,
'env_args' => [
],
'allow_sandbox_access' => true,
'allow_instances_access' => false,
'allow_tunnel_access' => true,
'timeout_minutes' => 123,
'custom_secrets' => [
],
'sampling_args' => [
],
'max_concurrent' => 4503599627370496,
'auto_max_concurrent' => false,
'max_retries' => 4503599627370495,
'state_columns' => [
'<string>'
],
'independent_scoring' => false,
'verbose' => false,
'headers' => [
'<string>'
],
'extra_env_kwargs' => [
],
'api_client_type' => '<string>',
'api_base_url' => '<string>',
'api_key_var' => '<string>'
],
'model_name' => '<string>',
'dataset' => '<string>',
'framework' => '<string>',
'task_type' => '<string>',
'description' => '<string>',
'tags' => [
],
'metadata' => [
],
'metrics' => [
],
'is_public' => false,
'show_on_leaderboard' => false
]),
CURLOPT_HTTPHEADER => [
"Authorization: Bearer <token>",
"Content-Type: application/json"
],
]);
$response = curl_exec($curl);
$err = curl_error($curl);
curl_close($curl);
if ($err) {
echo "cURL Error #:" . $err;
} else {
echo $response;
}package main
import (
"fmt"
"strings"
"net/http"
"io"
)
func main() {
url := "https://api.primeintellect.ai/api/v1/evaluations/"
payload := strings.NewReader("{\n \"name\": \"<string>\",\n \"team_id\": \"<string>\",\n \"environments\": [\n {\n \"id\": \"<string>\",\n \"version_id\": \"<string>\"\n }\n ],\n \"suite_id\": \"<string>\",\n \"run_id\": \"<string>\",\n \"is_hosted\": false,\n \"inference_model\": \"<string>\",\n \"eval_config\": {\n \"num_examples\": 4503599627370495,\n \"rollouts_per_example\": 1024,\n \"env_args\": {},\n \"allow_sandbox_access\": true,\n \"allow_instances_access\": false,\n \"allow_tunnel_access\": true,\n \"timeout_minutes\": 123,\n \"custom_secrets\": {},\n \"sampling_args\": {},\n \"max_concurrent\": 4503599627370496,\n \"auto_max_concurrent\": false,\n \"max_retries\": 4503599627370495,\n \"state_columns\": [\n \"<string>\"\n ],\n \"independent_scoring\": false,\n \"verbose\": false,\n \"headers\": [\n \"<string>\"\n ],\n \"extra_env_kwargs\": {},\n \"api_client_type\": \"<string>\",\n \"api_base_url\": \"<string>\",\n \"api_key_var\": \"<string>\"\n },\n \"model_name\": \"<string>\",\n \"dataset\": \"<string>\",\n \"framework\": \"<string>\",\n \"task_type\": \"<string>\",\n \"description\": \"<string>\",\n \"tags\": [],\n \"metadata\": {},\n \"metrics\": {},\n \"is_public\": false,\n \"show_on_leaderboard\": false\n}")
req, _ := http.NewRequest("POST", url, payload)
req.Header.Add("Authorization", "Bearer <token>")
req.Header.Add("Content-Type", "application/json")
res, _ := http.DefaultClient.Do(req)
defer res.Body.Close()
body, _ := io.ReadAll(res.Body)
fmt.Println(string(body))
}HttpResponse<String> response = Unirest.post("https://api.primeintellect.ai/api/v1/evaluations/")
.header("Authorization", "Bearer <token>")
.header("Content-Type", "application/json")
.body("{\n \"name\": \"<string>\",\n \"team_id\": \"<string>\",\n \"environments\": [\n {\n \"id\": \"<string>\",\n \"version_id\": \"<string>\"\n }\n ],\n \"suite_id\": \"<string>\",\n \"run_id\": \"<string>\",\n \"is_hosted\": false,\n \"inference_model\": \"<string>\",\n \"eval_config\": {\n \"num_examples\": 4503599627370495,\n \"rollouts_per_example\": 1024,\n \"env_args\": {},\n \"allow_sandbox_access\": true,\n \"allow_instances_access\": false,\n \"allow_tunnel_access\": true,\n \"timeout_minutes\": 123,\n \"custom_secrets\": {},\n \"sampling_args\": {},\n \"max_concurrent\": 4503599627370496,\n \"auto_max_concurrent\": false,\n \"max_retries\": 4503599627370495,\n \"state_columns\": [\n \"<string>\"\n ],\n \"independent_scoring\": false,\n \"verbose\": false,\n \"headers\": [\n \"<string>\"\n ],\n \"extra_env_kwargs\": {},\n \"api_client_type\": \"<string>\",\n \"api_base_url\": \"<string>\",\n \"api_key_var\": \"<string>\"\n },\n \"model_name\": \"<string>\",\n \"dataset\": \"<string>\",\n \"framework\": \"<string>\",\n \"task_type\": \"<string>\",\n \"description\": \"<string>\",\n \"tags\": [],\n \"metadata\": {},\n \"metrics\": {},\n \"is_public\": false,\n \"show_on_leaderboard\": false\n}")
.asString();require 'uri'
require 'net/http'
url = URI("https://api.primeintellect.ai/api/v1/evaluations/")
http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true
request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n \"name\": \"<string>\",\n \"team_id\": \"<string>\",\n \"environments\": [\n {\n \"id\": \"<string>\",\n \"version_id\": \"<string>\"\n }\n ],\n \"suite_id\": \"<string>\",\n \"run_id\": \"<string>\",\n \"is_hosted\": false,\n \"inference_model\": \"<string>\",\n \"eval_config\": {\n \"num_examples\": 4503599627370495,\n \"rollouts_per_example\": 1024,\n \"env_args\": {},\n \"allow_sandbox_access\": true,\n \"allow_instances_access\": false,\n \"allow_tunnel_access\": true,\n \"timeout_minutes\": 123,\n \"custom_secrets\": {},\n \"sampling_args\": {},\n \"max_concurrent\": 4503599627370496,\n \"auto_max_concurrent\": false,\n \"max_retries\": 4503599627370495,\n \"state_columns\": [\n \"<string>\"\n ],\n \"independent_scoring\": false,\n \"verbose\": false,\n \"headers\": [\n \"<string>\"\n ],\n \"extra_env_kwargs\": {},\n \"api_client_type\": \"<string>\",\n \"api_base_url\": \"<string>\",\n \"api_key_var\": \"<string>\"\n },\n \"model_name\": \"<string>\",\n \"dataset\": \"<string>\",\n \"framework\": \"<string>\",\n \"task_type\": \"<string>\",\n \"description\": \"<string>\",\n \"tags\": [],\n \"metadata\": {},\n \"metrics\": {},\n \"is_public\": false,\n \"show_on_leaderboard\": false\n}"
response = http.request(request)
puts response.read_body{
"evaluation_id": "<string>",
"name": "<string>",
"created_at": "2023-11-07T05:31:56Z",
"environment_ids": [
"<string>"
],
"suite_id": "<string>",
"run_id": "<string>",
"version_id": "<string>",
"viewer_url": "<string>"
}{
"errors": [
{
"param": "<string>",
"details": "<string>"
}
]
}Authorizations
Bearer authentication header of the form Bearer <token>, where <token> is your auth token.
Body
application/json
Request to create a new evaluation
Name of the evaluation
Team ID if creating evaluation for a team
List of environment references with optional version IDs
Show child attributes
Show child attributes
Suite ID if this evaluation is part of a suite
Run ID for Prime RL runs (optional)
Whether this is a hosted evaluation
Prime Inference model ID
Hosted evaluation configuration
Show child attributes
Show child attributes
Model name
Dataset name
Framework used (e.g., 'prime-rl', 'openai/evals')
Type of task (e.g., 'classification', 'generation')
Description of the evaluation
Tags for categorization
Additional metadata
High-level metrics summary
Whether this evaluation is publicly shareable by link
Whether this public evaluation appears on environment leaderboards
Response
Successful Response
Response after creating an evaluation
ID of the created evaluation
Evaluation status enum
Available options:
PENDING, RUNNING, PROCESSING, COMPLETED, FAILED, TIMEOUT, CANCELLED Type: 'prime_rl', 'environment', or 'suite'
Available options:
suite, training, environment Was this page helpful?
⌘I