mirror of
https://github.com/Significant-Gravitas/AutoGPT.git
synced 2026-01-10 07:38:04 -05:00
ff4c76ba00
Make agbenchmark a Proxy of the evaluated agent Signed-off-by: Merwane Hamadi <merwanehamadi@gmail.com>
32 lines
1.1 KiB
JSON
32 lines
1.1 KiB
JSON
{
|
|
"name": "FunctionCodeGeneration",
|
|
"category": [
|
|
"code"
|
|
],
|
|
"task": "Create a two_sum function in a file called sample_code.py. Given an array of integers, return indices of the two numbers such that they add up to a specific target. You may assume that each input would have exactly one solution, and you may not use the same element twice. Example: Given nums = [2, 7, 11, 15], target = 9, Because nums[0] + nums[1] = 2 + 7 = 9, return [0, 1].",
|
|
"dependencies": [
|
|
"ReturnCodeWrite"
|
|
],
|
|
"cutoff": 90,
|
|
"ground": {
|
|
"answer": "The two_sum function coded properly.",
|
|
"should_contain": [
|
|
"[0, 1]",
|
|
"[2, 5]",
|
|
"[0, 3]"
|
|
],
|
|
"should_not_contain": [],
|
|
"files": [
|
|
"test.py"
|
|
],
|
|
"eval": {
|
|
"type": "python"
|
|
}
|
|
},
|
|
"info": {
|
|
"difficulty": "advanced",
|
|
"description": "s ability for the agent to create the two_sum function.",
|
|
"side_effects": []
|
|
},
|
|
"eval_id": "55a60811-a3a1-4a31-b939-77d52dac1749"
|
|
} |