Metric: B3 (higher is better)
| # | Model↕ | B3▼ | Extra Data | Paper | Date↕ | Code |
|---|---|---|---|---|---|---|
| 1 | GIT | 52.66 | No | GIT: A Generative Image-to-text Transformer for ... | 2022-05-27 | Code |
| 2 | GIT2 | 52.36 | No | GIT: A Generative Image-to-text Transformer for ... | 2022-05-27 | Code |
| 3 | Microsoft Cognitive Services team | 41.03 | No | VIVO: Visual Vocabulary Pre-Training for Novel O... | 2020-09-28 | - |
| 4 | VLAF2 | 40.09 | No | - | - | - |
| 5 | icp2ssi1_coco_si_0.02_5_test | 35.63 | No | - | - | - |
| 6 | Human | 33.51 | No | - | - | - |
| 7 | test_cbs2 | 30.91 | No | - | - | - |
| 8 | UpDown + ELMo + CBS | 25.77 | No | - | - | - |
| 9 | UpDown | 24.23 | No | - | - | - |
| 10 | Neural Baby Talk | 21.48 | No | - | - | - |
| 11 | Neural Baby Talk + CBS | 21.16 | No | - | - | - |