IG-VLM-34B

Reported on 4 benchmarks across 2 tasks · 1 paper

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

Natural Language Processing2 results

Question AnsweringonMSVD-QA
Accuracy· 2024-03-27
79.6
best: 80.3 (Tarsier (34B))
An Image Grid Can Be Worth a Video: Zero-shot Video Question Answering Using a VLM arXiv:2403.18406
Question AnsweringonMSVD-QA
Confidence Score· 2024-03-27
4.1
best: 2.5 (Video LLaMA-7B)
An Image Grid Can Be Worth a Video: Zero-shot Video Question Answering Using a VLM arXiv:2403.18406

Reasoning2 results

Video Question AnsweringonMSVD-QA
Accuracy· 2024-03-27
79.6
best: 80.3 (Tarsier (34B))
An Image Grid Can Be Worth a Video: Zero-shot Video Question Answering Using a VLM arXiv:2403.18406
Video Question AnsweringonMSVD-QA
Confidence Score· 2024-03-27
4.1
best: 2.5 (Video LLaMA-7B)
An Image Grid Can Be Worth a Video: Zero-shot Video Question Answering Using a VLM arXiv:2403.18406