ARC Prize evaluates Inkling 2 Small: 81.7% score on ARC-AGI-2
ARC Prize has published the verification results for Thinking Machines' Inkling 2 Small on ARC-AGI: 81.7% score on ARC-AGI-2 at $0.27 per task; 96.5% score on ARC-AGI-1 at $0.08 per task. Compared with the first-generation Inkling Small released on July 30, the ARC-AGI-2 semi-private set score rose from 40.14% to 81.67%. ARC Prize states that it surpasses all open-weight models it has evaluated on ARC-AGI-1 and ARC-AGI-2; Thinking Machines plans to release the full weights next week, and ARC-AGI-3 results will be announced after testing is complete.
Why read this
AI score 78
ARC Prize provides Inkling 2 Small's scores on ARC-AGI-1 and ARC-AGI-2 along with per-task cost, directly comparable with the previous generation.
Topics
Body
@thinkymachines Compared with the original Inkling Small, released July 30, Inkling 2 Small more than doubled the ARC-AGI-2 semi-private score, from 40.14% to 81.67%. https://t.co/kwy8zygwKj