GPT-4o +text rationale +IoT

Reported on 2 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 Processing2 results

Visual Question Answering (VQA)onMM-Vet
GPT-4 score· 2024-05-22
72.2
best: 74.24 (MMCTAgent (GPT-4 + GPT-4V))
SOTA
Image-of-Thought Prompting for Visual Reasoning Refinement in Multimodal Large Language Models arXiv:2405.13872
Visual Question AnsweringonMM-Vet
GPT-4 score· 2024-05-22
72.2
best: 74.24 (MMCTAgent (GPT-4 + GPT-4V))
SOTA
Image-of-Thought Prompting for Visual Reasoning Refinement in Multimodal Large Language Models arXiv:2405.13872