Visual Question Answering On Benchlmm
Métriques
GPT-3.5 score
Résultats
Résultats de performance de divers modèles sur ce benchmark
Tableau comparatif
| Nom du modèle | GPT-3.5 score |
|---|---|
| minigpt-4-enhancing-vision-language | 34.93 |
| instructblip-towards-general-purpose-vision | 44.63 |
| improved-baselines-with-visual-instruction | 55.53 |
| sphinx-the-joint-mixing-of-weights-tasks-and | 57.43 |
| visual-instruction-tuning-1 | 46.83 |
| instructblip-towards-general-purpose-vision | 45.03 |
| minigpt-v2-large-language-model-as-a-unified | 30.1 |
| gpt-4-technical-report-1 | 58.37 |
| visual-instruction-tuning-1 | 43.50 |
| otter-a-multi-modal-model-with-in-context | 39.13 |