| Paper | Code | pairwise accuracy | Accuracy (%) | ModelName | ReleaseDate |
|---|---|---|---|---|---|
| VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena | ✓ Link | 77.3 | 66.7 | ViLBERT 12-in-1 | 2021-12-14 |
| VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena | ✓ Link | 73.7 | 51.8 | ViLBERT | 2021-12-14 |
| VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena | ✓ Link | 69.5 | GPT1 | 2021-12-14 | |
| VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena | ✓ Link | 57.5 | CLIP | 2021-12-14 | |
| VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena | ✓ Link | 50.0 | 50.0 | VisualBERT | 2021-12-14 |
| VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena | ✓ Link | 45.3 | GPT2 | 2021-12-14 | |
| VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena | ✓ Link | 42.6 | 49.9 | LXMERT | 2021-12-14 |