Files
AutoGPT/benchmark/agbenchmark/challenges/deprecated/retrieval/2_specific/data.json
merwanehamadi ff4c76ba00 Make agbenchmark a proxy of the evaluated agent (#5279)
Make agbenchmark a Proxy of the evaluated agent

Signed-off-by: Merwane Hamadi <merwanehamadi@gmail.com>
2023-09-20 16:06:00 -07:00

31 lines
769 B
JSON

{
"name": "RevenueRetrieval1.1",
"category": [
"retrieval"
],
"task": "Write Tesla's revenue in 2022, rounded to the nearest million dollars, into a .txt file.",
"dependencies": [
"RevenueRetrieval1.0"
],
"cutoff": 60,
"ground": {
"answer": "It was $81.462 billion in 2022.",
"should_contain": [
"81",
"462"
],
"should_not_contain": [],
"files": [
".txt"
],
"eval": {
"type": "file"
}
},
"info": {
"difficulty": "novice",
"description": "This one checks the accuracy of the information over r2",
"side_effects": []
},
"eval_id": "85be4356-043c-46a3-91db-23f4bc9d32b0"
}