We are releasing HLE-Diamond, a refined subset of Humanity’s Last Exam (HLE), following…
This is a AI post classified by Jev as Frontier models (a model release), kept by the AI Radar because it carries real work, not commentary.
We are releasing HLE-Diamond, a refined subset of Humanity’s Last Exam (HLE), following a year-long process of cleaning and refinement with input from various research communities. https://lastexam.ai/blog/hle-diamond w/ @ScaleAILabs
Posted by Center for AI Safety (12.1k followers) 2 h ago · 310 likes · 14.2k views · view the original post on X. Kept by the AI Radar as Frontier models. Tools mentioned: Humanity's Last Exam.
More AI work like this
- GPT-6 Sol recreates The Nihilist Penguin in Blender — @aimlapi
- i've been trying to run warden security benchmarks against 4.7 since yesterday and it… — @grichadev
- My prompt was "Generate Teenage Engineering's OP-1". — @zachdive
- Claude Opus 5.5 vs GPT-6 Sol in building game worlds. — @higgsfield_ai
- Opus 5.5 is now the default model in Adam. — @adamdotnew
- Opus 5.5 is the most fun model I’ve ever used. — @AiBreakfast
- BREAKING: OpenAI's GPT-6 Astra successfully drove a real Toyota Corolla through an… — @exec_sum
- BREAKING: OpenAI's GPT-6 Astra successfully drove a real Toyota Corolla through an… — @exec_sum
Every post is read and classified by Jev (TypeSafe): what it is, which market it belongs to, and whether the link is a real tool. 44.7k posts from 5k X accounts over the last 14 days, 1.9k tools, 19 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-23 17:53 UTC. Full method.