Inkling Small from
- Full results: arcprize.org/results/thinky…ARC-AGI-3 evaluations are more operationally intensive, so results will roll out over the next few weeks.- Leaderboard:arcprize.org/leaderboard- Reproduce the public results:github.com/arcprize/arc-a…- Testing policy:arcprize.org/policy- Full Inkling Small results:arcprize.org/results/thinky… - Wow almost on par with gpt 5.2 high! For such a small model, it's incredible.
source & further reading
twitter.com — original article