| Paper | Code | average pairwise accuracy | Average Accuracy | ModelName | ReleaseDate |
|---|---|---|---|---|---|
| VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena | ✓ Link | 75.1 | 63.2 | ViLBERT 12-in-1 | 2021-12-14 |
| VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena | ✓ Link | 64.0 | CLIP | 2021-12-14 | |
| VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena | ✓ Link | 63.7 | 51.3 | ViLBERT | 2021-12-14 |
| VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena | ✓ Link | 60.7 | GPT1 | 2021-12-14 | |
| VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena | ✓ Link | 60.1 | GPT2 | 2021-12-14 | |
| VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena | ✓ Link | 59.6 | 53.5 | LXMERT | 2021-12-14 |
| VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena | ✓ Link | 46.4 | 48.8 | VisualBERT | 2021-12-14 |