APIBench
Benchmarks
Task NameDataset NameSOTA ResultTrendResults
APIBench HF (test)
83.2Accuracy
12
APIBench
79.2HuggingFace AST Accuracy
8
APIBench OOD - TensorHub
2.04Hallucination Rate
6
APIBench OOD TorchHub
5.91Hallucination Rate
6
APIBench OOD HuggingFace
0.064Hallucination Rate
6
APIBench (test)
30.64Recall@1
4
APIBench TensorFlow Hub (test)
88.91Accuracy
4
APIBench Torch Hub (test)
93.55Accuracy
4
APIBench Hugging Face (test)
77.21Accuracy
4