tweetindex

ARC Prize @arcprize · 25 Mar 2026

Announcing ARC-AGI-3 The only unsaturated agentic intelligence benchmark in the world Humans score 100%, AI <1% This human-AI gap demonstrates we do not yet have AGI Most benchmarks test what models already know, ARC-AGI-3 tests how they learn https://t.co/BC2QaNZuvH
771 867Views
4 326Likes
570Reposts
258Replies
272Quotes
933Bookmarks

Is that a lot?

75.8×vs this author's median10 176 views is typical
100Percentile for this authorof 6 recent posts
281×vs 10K–100K median2 751 views is typical
18.8× audienceReachviews ÷ followers
0.70%Engagement rateof viewers reacted

Compare with the benchmark table →

Open on X →