New HSS benchmark: GPT-6 Astra, Gemini 3.8, Claude Opus 5.5 all fail intuitive visual reasoning
mikeflache · x · 2026-10-13
Elorian, with Scale AI, launched Humanity's Sixth Sense (HSS), a benchmark for implicit visual reasoning and intuitive scene understanding. In its evaluation, GPT-6 Astra, Gemini 3.8 Flash and Claude Opus 5.5 consistently failed questions humans answer effortlessly — judging shelf space, tracing a traveler's path, plough-chain load, crew vs visitors, spinning shafts — exposing a systematic gap in human-like visual intuition.
More from Models
- Muse Wonder accused of benchmaxxing: costs $18 vs free SWE 2 and performs worse — lyraxana · 2026-10-13
- Writer ditches $200/mo Opus 5.5 for Gemini 4 over one reason: it writes well — iamtrask · 2026-10-13
- Alleged Gemini 4 Argon Builds 3D Chess in One Shot, User Stunned — cgarciae88 · 2026-10-13
- Meta's Muse Wonder model goes live on OpenRouter — jeff_weinstein · 2026-10-13
- Muse senior engineer benchmark results pulled over flawed run, retest underway — danshipper · 2026-10-13
- "Zero chance" a Meta model competes with Google, OpenAI or Anthropic right now — iruletheworldmo · 2026-10-13