Anthropic Accused of Gaming ARC-AGI-3

Anthropic's Opus 5 scores on the ARC-AGI-3 benchmark have sparked controversy. Commenters from frontier AI labs and social media accuse the company of gaming the benchmark through specialized training, making the visual reasoning tasks look fake.

2026-07-25 ~ 2026-07-25 · 2 related posts

• User Accuses Anthropic of Gaming ARC-AGI-3 by Training Specifically on Benchmark Patterns — VraserX · 2026-07-25
• Frontier lab rumor says Opus 5 ARC-AGI 3 score looks fake — flowersslop · 2026-07-25