| Paper | Code | pairwise accuracy | Accuracy (%) | ModelName | ReleaseDate |
|---|---|---|---|---|---|
| VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena | ✓ Link | 80.2 | 69.2 | ViLBERT 12-in-1 | 2021-12-14 |
| VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena | ✓ Link | 69.2 | 55.4 | LXMERT | 2021-12-14 |
| VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena | ✓ Link | 62.9 | 50.6 | ViLBERT | 2021-12-14 |
| VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena | ✓ Link | 62.5 | CLIP | 2021-12-14 | |
| VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena | ✓ Link | 49.8 | GPT2 | 2021-12-14 | |
| VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena | ✓ Link | 48.7 | GPT1 | 2021-12-14 | |
| VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena | ✓ Link | 48.2 | 47.8 | VisualBERT | 2021-12-14 |