Anthropic Claude Opus 5 significantly leads GPT-5.6 Sol on the ARC-AGI-3 benchmark with a score of 30.2%, demonstrating new reasoning behaviors
Anthropic's Claude Opus 5 scored 30.2 percent on ARC-AGI-3, nearly quadrupling GPT-5.6 Sol's previous record of 7.8 percent.
Return to original text
A short introduction is retained here; the full text from the source website is not reposted. For specific wording and subsequent updates, please refer to the original article.
Open original at the-decoder.com