Anthropic's Opus 5 blows past Fable 5 and GPT-5.6 Sol on the benchmark designed to measure real intelligence

https://the-decoder.com/wp-content/uploads/2026/07/arc_agi_3_opus_5.png" style="height: auto; margin-bottom: 10px;" width="1376" />

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 stronger logical reasoning.

The article https://the-decoder.com/anthropics-opus-5-blows-past-fable-5-and-gpt-5-6-sol-on-the-benchmark-designed-to-measure-real-intelligence/">Anthropic's Opus 5 blows past Fable 5 and GPT-5.6 Sol on the benchmark designed to measure real intelligence appeared first on https://the-decoder.com">The Decoder.