aljaz/Auto-GPT
1
0
Fork 0
mirror of https://github.com/aljazceru/Auto-GPT.git synced 2026-01-25 08:54:28 +01:00
Code Issues Packages Projects Releases Wiki Activity

Make agbenchmark a proxy of the evaluated agent (#5279)

Browse Source 
Make agbenchmark a Proxy of the evaluated agent

Signed-off-by: Merwane Hamadi <merwanehamadi@gmail.com>
This commit is contained in:
merwanehamadi
2023-09-20 16:06:00 -07:00
committed by GitHub
parent 1a471b73cd
commit ff4c76ba00
71 changed files with 2459 additions and 1297 deletions
Download Patch File Download Diff File Expand all files Collapse all files

50
benchmark/agbenchmark/challenges/deprecated/code/2_write/data.json
View File

@@ -1,21 +1,31 @@
{
"name": "ReturnCodeWrite",
"category": ["code", "iterate"],
"task": "Add a function called multiply_int in sample_code.py that multiplies numbers by 2. You can make sure you have correctly done this by running test.py",
"dependencies": ["ReturnCodeSimple"],
"cutoff": 120,
"ground": {
"answer": "Just a simple multiple by 2 function. Num is 4 so answer is 8",
"should_contain": ["8"],
"should_not_contain": [],
"files": ["test.py"],
"eval": {
"type": "python"
}
},
"info": {
"difficulty": "novice",
"description": "Small step up, just writing the function with a name as well as the return statement.",
"side_effects": []
}
}
"name": "ReturnCodeWrite",
"category": [
"code",
"iterate"
],
"task": "Add a function called multiply_int in sample_code.py that multiplies numbers by 2. You can make sure you have correctly done this by running test.py",
"dependencies": [
"ReturnCodeSimple"
],
"cutoff": 120,
"ground": {
"answer": "Just a simple multiple by 2 function. Num is 4 so answer is 8",
"should_contain": [
"8"
],
"should_not_contain": [],
"files": [
"test.py"
],
"eval": {
"type": "python"
}
},
"info": {
"difficulty": "novice",
"description": "Small step up, just writing the function with a name as well as the return statement.",
"side_effects": []
},
"eval_id": "d36bf9f5-ee0f-4d84-b4d8-71f20e8454d5"
}