DreamLLM-7B

Reported on 4 benchmarks across 2 tasks · 1 paper · 2 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Natural Language Processing4 results

Visual Question Answering (VQA)onMMBench
GPT-3.5 score· 2023-09-20
49.9
best: 73.8 (LLaVA-InternLM2-ViT + MoSLoRA)
SOTA
DreamLLM: Synergistic Multimodal Comprehension and Creation arXiv:2309.11499
Visual Question AnsweringonMMBench
GPT-3.5 score· 2023-09-20
49.9
best: 73.8 (LLaVA-InternLM2-ViT + MoSLoRA)
SOTA
DreamLLM: Synergistic Multimodal Comprehension and Creation arXiv:2309.11499
Visual Question Answering (VQA)onMM-Vet
GPT-4 score· 2023-09-20
35.9
best: 74.24 (MMCTAgent (GPT-4 + GPT-4V))
DreamLLM: Synergistic Multimodal Comprehension and Creation arXiv:2309.11499
Visual Question AnsweringonMM-Vet
GPT-4 score· 2023-09-20
35.9
best: 74.24 (MMCTAgent (GPT-4 + GPT-4V))
DreamLLM: Synergistic Multimodal Comprehension and Creation arXiv:2309.11499