LLaVA-OneVision-72B

Reported on 4 benchmarks across 4 tasks · 1 paper

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

Natural Language Processing3 results

Question AnsweringonVNBench
Accuracy· 2024-08-06
58.7
best: 77.88 (BIMBA-LLaVA-Qwen2-7B)
LLaVA-OneVision: Easy Visual Task Transfer arXiv:2408.03326
Visual Question Answering (VQA)onMM-Vet
GPT-4 score· 2024-08-06
63.7
best: 74.24 (MMCTAgent (GPT-4 + GPT-4V))
LLaVA-OneVision: Easy Visual Task Transfer arXiv:2408.03326
Visual Question AnsweringonMM-Vet
GPT-4 score· 2024-08-06
63.7
best: 74.24 (MMCTAgent (GPT-4 + GPT-4V))
LLaVA-OneVision: Easy Visual Task Transfer arXiv:2408.03326

Reasoning1 result

Video Question AnsweringonVNBench
Accuracy· 2024-08-06
58.7
best: 77.88 (BIMBA-LLaVA-Qwen2-7B)
LLaVA-OneVision: Easy Visual Task Transfer arXiv:2408.03326