AI labsUnited States
LLaVA Authors models
The LLaVA research collaboration develops open-weight vision-language models and evaluation resources. It publishes model artifacts, datasets, papers, and leaderboards for the LLaVA and LLaVA-OneVision families.
- Scored models
- 3
- Best ranked
- LLaVA-OneVision 72B #531 of 896
- Newest
- LLaVA-OneVision 72B Aug 6, 2024
- Open weights
- 3 of 3
LLaVA Authors models ranked by capability
Capability is Atlas's single score for each model, fitted to every sourced benchmark result (methodology). Rank is among all 896 ranked models from every lab. The 1 model without enough scores for a capability estimate follow, newest first.
| Model | Released | Capability | Rank | Benchmarks | Weights |
|---|---|---|---|---|---|
| LLaVA-OneVision 72B | Aug 6, 2024 | 118.7 | #531 | 13 | Open |
| LLaVA v1.5 7B | Oct 5, 2023 | 81.7 | #838 | 7 | Open |
| LLaVA v1.6 Mistral 7B | Jan 30, 2024 | — | — | 2 | Open |