← Back
ARC-AGI
A benchmark test designed to measure artificial general intelligence capabilities through abstract reasoning challenges.
1
sources
Mentioned by
All mentions
"I remember when you first came out with your paper in December of last year, uh you shot to the top of ARC-AGI V2 and then you've done this a bunch of times for other benchmarks too."
Attribution: Y Combinator host mentions ARC-AGI as a benchmark that Poetic performed well on