Humanity's Sixth Sense: Benchmarking Intuitive Visual Reasoning in Multimodal Models

2026-10-06

AI Summary

This study addresses the oversight of intuitive visual reasoning in existing multimodal benchmarks by introducing HSS, which establishes intuitive visual reasoning as a quantifiable evaluation dimension for the first time. Encompassing spatiotemporal, social, and abstract implicit information, this benchmark bridges the gap between low-level perception and high-level cognitive analysis through a structured taxonomy, manual prompt engineering, and agent-based dynamic visual manipulation techniques. Experimental results demonstrate that the best-performing model achieves an accuracy of only 53.6%, substantially lagging behind the human baseline of 93.1%. This significant performance disparity reveals critical deficiencies in the intuitive reasoning capabilities of current multimodal large language models, highlighting the necessity for further advancement in this domain.

Abstract

Humans perceive far more in a scene than what is explicitly depicted: a single glance captures past causes and future trajectories; a quick peek determines if a vehicle can fit between two parked cars; a few seconds of video reveals who holds authority in a room; and a fleeting clip highlights subtle abstract patterns like unwritten rules or hidden labels. This capacity reflects a form of humanity's sixth sense: an intuitive reasoning mechanism that recovers implicit information beyond raw sensory perception. Crucially, this rapid, zero-shot visual intuition underpins everyday navigation and social interaction, making it a vital capability for Multimodal Large Language Models (MLLMs) deployed alongside people. Existing visual benchmarks, however, target either deliberate expert-level analysis in academic and mathematical domains or low-level perception, leaving the intuitive reasoning that people perform largely untested. To bridge this gap, we introduce Humanity's Sixth Sense (HSS), a benchmark for intuitive visual reasoning. HSS spans diverse image and video inputs, organizes items under a structured taxonomy, and pairs each with human-written prompts probing the implicit temporal, spatial, social, and abstract structure that people infer at a glance. Frontier MLLMs fall short of human performance: participants reach 93.1% accuracy, while the strongest model, GPT-6-astra, reaches only 53.6% even at maximum reasoning effort. Despite excelling in many complex tasks that require advanced perception and knowledge, current models still struggle significantly on these visual tasks that are intuitive for humans. We further explore agentic setup that apply dynamic visual manipulation to HSS, which narrows but does not close the gap. HSS establishes intuitive visual reasoning as a measurable axis and directs attention to a capability that scaling on current benchmarks has so far left behind.

Problem

• Intuitive Visual Reasoning
• Multimodal Large Language Models
• Benchmark
• Implicit Information
• Sixth Sense

Innovation

• Intuitive Visual Reasoning
• Multimodal Benchmark
• Humanity's Sixth Sense
• Agentic Setup
• Implicit Information Inference