| Paper | Code | Average Accuracy | Average Precision | Average Recall | Average F1 | ModelName | ReleaseDate |
|---|---|---|---|---|---|---|---|
| Learning Type Inference for Enhanced Dataflow Analysis | ✓ Link | 71.27 | CodeTIDAL5 | 2023-10-01 | |||
| ManyTypes4TypeScript: A Comprehensive TypeScript Dataset for Sequence-Based Type Inference | ✓ Link | 63.42 | GraphCodeBERT-MT4TS | 2022-10-17 | |||
| GraphCodeBERT: Pre-training Code Representations with Data Flow | ✓ Link | 62.51 | 60.06 | 61.08 | 60.57 | GraphCodeBERT | 2020-09-17 |
| CodeBERT: A Pre-Trained Model for Programming and Natural Languages | ✓ Link | 61.72 | 59.34 | 59.80 | 59.57 | CodeBERT | 2020-02-19 |
| Multilingual training for Software Engineering | 61.29 | 58.81 | 58.91 | 58.86 | PolyGot | 2021-12-03 | |
| Multilingual training for Software Engineering | 61.00 | 58.36 | 58.91 | 58.63 | GraphPolyGot | 2021-12-03 | |
| RoBERTa: A Robustly Optimized BERT Pretraining Approach | ✓ Link | 59.84 | 57.45 | 57.62 | 57.54 | RoBERTa | 2019-07-26 |
| []() | 59.81 | 56.57 | 56.85 | 56.71 | CodeBERTa | ||
| BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding | ✓ Link | 57.52 | 54.18 | 54.02 | 54.10 | BERT | 2018-10-11 |