Skip to content
Loading…
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. The benchmark's developers say the model independently formulated reflection equations, a behavior they had never seen from another model, and attribute…
To respect copyright, we link to the source rather than republishing the full text. Read the complete article on The Decoder.