---
format: "aidr-story-markdown/v1"
id: "55bdc1874a8eea57d926c34e9fc01d8e4e1ff0f95fe64e4c3f0f2075a8dde584"
canonical_url: "https://aidr.today/55bdc187?lang=en"
title: "GPT-6-astra Scores 53.6% on New Humanity's Sixth Sense Benchmark"
lang: "en"
requested_lang: "en"
available_langs: ["en","vi"]
translation_fallback: null
fallback_fields: []
published_at: "2026-10-08T02:52:35.000Z"
category: "Research"
topics: ["openai","reasoning"]
source_urls: ["https://marketbrief.now/ai/gpt-6-astra-scores-536percent-on-new-humanitys-sixth-sense-benchmark-14232354","https://huggingnews.com/ai/gpt-6-astra-scores-536percent-on-new-humanitys-sixth-sense-benchmark-14232354"]
summary: "Scale AI and Elorian AI released the Humanity's Sixth Sense benchmark, a multimodal evaluation testing spatial, causal, and social reasoning across 522 open-ended tasks, where GPT-6-astra scored 53.6% compared to a median AI score of 30.9% and a human average of 93.1%."
---

# GPT\-6\-astra Scores 53\.6% on New Humanity's Sixth Sense Benchmark

> [Open the canonical story](<https://aidr.today/55bdc187?lang=en>)

**Published:** 2026-10-08T02:52:35.000Z
**Category:** Research
**Topics:** openai, reasoning

## Summary

Scale AI and Elorian AI released the Humanity's Sixth Sense benchmark, a multimodal evaluation testing spatial, causal, and social reasoning across 522 open\-ended tasks, where GPT\-6\-astra scored 53\.6% compared to a median AI score of 30\.9% and a human average of 93\.1%\.

## Sources

- [Story source](<https://marketbrief.now/ai/gpt-6-astra-scores-536percent-on-new-humanitys-sixth-sense-benchmark-14232354>)
- [Story source](<https://huggingnews.com/ai/gpt-6-astra-scores-536percent-on-new-humanitys-sixth-sense-benchmark-14232354>)