Metric: B1 (higher is better)
| # | Model↕ | B1▼ | Extra Data | Paper | Date↕ | Code |
|---|---|---|---|---|---|---|
| 1 | GIT2 | 86.28 | No | GIT: A Generative Image-to-text Transformer for ... | 2022-05-27 | Code |
| 2 | GIT | 85.99 | No | GIT: A Generative Image-to-text Transformer for ... | 2022-05-27 | Code |
| 3 | VLAF2 | 79.59 | No | - | - | - |
| 4 | Microsoft Cognitive Services team | 79.44 | No | VIVO: Visual Vocabulary Pre-Training for Novel O... | 2020-09-28 | - |
| 5 | icp2ssi1_coco_si_0.02_5_test | 75.59 | No | - | - | - |
| 6 | Human | 74.84 | No | - | - | - |
| 7 | test_cbs2 | 74.5 | No | - | - | - |
| 8 | UpDown + ELMo + CBS | 71.57 | No | - | - | - |
| 9 | UpDown | 66.54 | No | - | - | - |
| 10 | Neural Baby Talk + CBS | 65.98 | No | - | - | - |
| 11 | Neural Baby Talk | 64.45 | No | - | - | - |