Visual Instruction Following On Llava Bench
평가 지표
avg score
평가 결과
이 벤치마크에서 각 모델의 성능 결과
비교 표
| 모델 이름 | avg score |
|---|---|
| sharegpt4v-improving-large-multi-modal-models | 79.9 |
| cumo-scaling-multimodal-llm-with-co-upcycled | 85.7 |
| improved-baselines-with-visual-instruction | 70.7 |
| instructblip-towards-general-purpose-vision | 58.2 |
| blip-2-bootstrapping-language-image-pre | 38.1 |
| sharegpt4v-improving-large-multi-modal-models | 72.6 |
| instructblip-towards-general-purpose-vision | 60.9 |
| improved-baselines-with-visual-instruction | 63.4 |