| Paper | Code | pairwise accuracy | Accuracy (%) | ModelName | ReleaseDate |
|---|---|---|---|---|---|
| VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena | ✓ Link | 76.9 | GPT2 | 2021-12-14 | |
| VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena | ✓ Link | 72.2 | GPT1 | 2021-12-14 | |
| VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena | ✓ Link | 68.6 | CLIP | 2021-12-14 | |
| VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena | ✓ Link | 68.3 | 50.4 | ViLBERT | 2021-12-14 |
| VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena | ✓ Link | 58.9 | 52.2 | ViLBERT 12-in-1 | 2021-12-14 |
| VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena | ✓ Link | 45.8 | 48.5 | LXMERT | 2021-12-14 |
| VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena | ✓ Link | 44.4 | 49.7 | VisualBERT | 2021-12-14 |