Model card
GraphCodeBERT+AdvFusion.
University of Leicesteropen-weights125M paramstransformer
GraphCodeBERT fine-tuned with Adversarial Adapter Fusion; AdvFusion Dec 2024
§ 01 · Benchmarks
Every benchmark GraphCodeBERT+AdvFusion has a recorded score for.
| # | Benchmark | Area · Task | Metric | Value | Rank | Date | Source |
|---|---|---|---|---|---|---|---|
| 01 | codesearchnet---javascript | Computer Vision · Optical Character Recognition | smoothed-bleu-4 | 15.9% | #5 | 2024-12-01 | source ↗ |
Rank column shows this model’s position vs all other models scored on the same benchmark + metric (competitors after the slash). #1 in red means current SOTA. Sorted by rank, then newest result.
§ 02 · Strengths by area
Where GraphCodeBERT+AdvFusion actually performs.
§ 03 · Papers
1 paper with results for GraphCodeBERT+AdvFusion.
§ 04 · Related models
Other University of Leicester models scored on Codesota.
§ 05 · Sources & freshness
Where these numbers come from.
AdvFusion paper (IEEE TSE 2024)
1
result
1 of 1 rows marked verified.