Discussion

GPT-5.5 – No ARC-AGI-3 scores

Did the model perform poorly and OpenAI decided to not publish arc agi 3 scores? This is honestly the best benchmark right now to measure true intelligence.
25 points AG25 6 months ago 3 comments

Discussion

Live from the official Hacker News API

A modern reader for Hacker News · SvelteKit + Skeleton