Temporal Casual Qa On Next Qa
Métriques
WUPS
Résultats
Résultats de performance de divers modèles sur ce benchmark
Tableau comparatif
| Nom du modèle | WUPS |
|---|---|
| flamingo-a-visual-language-model-for-few-shot-1 | 26.7 |
| pali-x-on-scaling-up-a-multilingual-vision | 38.3 |
| pali-3-vision-language-models-smaller-faster | 37.7 |
| retrieving-to-answer-zero-shot-video-question | 34.7 |
| flamingo-a-visual-language-model-for-few-shot-1 | 33.5 |
| generative-pretraining-in-multimodality | 23.4 |
| gemini-a-family-of-highly-capable-multimodal-1 | 29.9 |
| gemini-a-family-of-highly-capable-multimodal-1 | 28.0 |