17:18
2026-07-24
officechai.com
artificial-intelligence
Claude Opus Scores 30% On ARC-AGI 3, Triples Previous Best Score By Any Model
Anthropic's Claude Opus 5 has posted a 30.2% score on ARC-AGI-3, more than tripling the previous best result of 7.8% held by GPT-5.6 Sol. The benchmark, designed by François Chollet to measure fluid i…