code_eval_outputs / tests.py
giulio98's picture
add test
d10963a
raw
history blame
521 Bytes
test_cases = [
{
"candidates": ["def add(a,b):\n return a*b\n", "def add(a, b):\n return a+b\n"],
"references": ["if __name__ == \"__main__\":\n print(add(2, 3))\n"],
"output" : ["5"]
"result": {"metric_score": 0.5}
},
{
"candidates": ["def add(a,b):\n return a*b\n", "def add(a, b):\n return a^b\n"],
"references": ["if __name__ == \"__main__\":\n print(add(2, 3))\n"],
"output" : ["5"]
"result": {"metric_score": 0.0}
}
]