benchmark_summary_cognee.json•1.75 kB
[
{
"system": "Cognee Graph Completion CoT",
"Human-like Correctness": 0.925,
"Human-like Correctness Error": [
0.911,
0.94
],
"DeepEval Correctness": 0.846,
"DeepEval Correctness Error": [
0.83,
0.863
],
"DeepEval EM": 0.687,
"DeepEval EM Error": [
0.661,
0.717
],
"DeepEval F1": 0.841,
"DeepEval F1 Error": [
0.821,
0.861
]
},
{
"system": "Cognee Graph Completion Context Extension",
"Human-like Correctness": 0.871,
"Human-like Correctness Error": [
0.852,
0.891
],
"DeepEval Correctness": 0.785,
"DeepEval Correctness Error": [
0.765,
0.805
],
"DeepEval EM": 0.617,
"DeepEval EM Error": [
0.589,
0.645
],
"DeepEval F1": 0.776,
"DeepEval F1 Error": [
0.755,
0.797
]
},
{
"system": "Cognee Graph Completion",
"Human-like Correctness": 0.805,
"Human-like Correctness Error": [
0.783,
0.827
],
"DeepEval Correctness": 0.743,
"DeepEval Correctness Error": [
0.723,
0.765
],
"DeepEval EM": 0.596,
"DeepEval EM Error": [
0.569,
0.625
],
"DeepEval F1": 0.724,
"DeepEval F1 Error": [
0.698,
0.749
]
},
{
"system": "Cognee (Previous Non-Optimized Evaluation)",
"Human-like Correctness": 0.738,
"Human-like Correctness Error": [
0.626,
0.842
],
"DeepEval Correctness": 0.569,
"DeepEval Correctness Error": [
0.494,
0.642
],
"DeepEval EM": 0.04,
"DeepEval EM Error": [
0.0,
0.1
],
"DeepEval F1": 0.203,
"DeepEval F1 Error": [
0.155,
0.255
]
}
]
