330K images with 5 captions each. Standard benchmark for image captioning.
6 results indexed across 3 metrics. Shaded row marks current SOTA; ties broken by submission date.
| # | Model | Org | Submitted | Paper / code | CIDEr |
|---|---|---|---|---|---|
| 01 | BLIP-2Open | Salesforce | Jan 2023 | BLIP-2: Bootstrapping Language-Image Pre-training with F… | 145.80 |
| 02 | CoCaOpen | May 2022 | CoCa: Contrastive Captioners are Image-Text Foundation M… | 143.60 |
| # | Model | Org | Submitted | Paper / code | cider |
|---|---|---|---|---|---|
| 01 | Chameleon-SFT | — | May 2024 | Chameleon: Mixed-Modal Early-Fusion Foundation Models · code | 140.80 |
| # | Model | Org | Submitted | Paper / code | r-1 |
|---|---|---|---|---|---|
| 01 | BLIP ViT-L | — | Jan 2022 | BLIP: Bootstrapping Language-Image Pre-training for Unif… · code | 65.10 |
| 02 | ALIGN | — | Feb 2021 | Scaling Up Visual and Vision-Language Representation Lea… · code | 59.90 |
| 03 | AltCLIP | — | Nov 2022 | AltCLIP: Altering the Language Encoder in CLIP for Exten… · code | 42.90 |
Each row below marks a model that broke the previous record on cider. Intermediate submissions are kept in the leaderboard above; only SOTA-setting entries are re-listed here.
Higher scores win. Each subsequent entry improved upon the previous best.
Every paper below corresponds to at least one row in the leaderboard above. Click through for the arXiv preprint and, when available, the reference implementation.
Submit a checkpoint and a reproduction script. We will run it, publish the score, and — if it takes the top — annotate the step on the progress chart with your name.