New
AI & RoboticsMore in AI & Robotics→
Claude Opus 5 Sets New ARC-AGI-3 Benchmark Lead
Key Takeaways
- Claude Opus 5 reportedly scored 30.2% on ARC-AGI-3.
- The previous top score cited in the source was 7.8% by GPT-5.6 Sol (Max).
- ARC Prize says the gap reflects stronger logical reasoning and autonomous planning.
- Researchers also reported unusual problem-solving behavior, including algebraic reformulation.
DE
DT Editorial Team··via the-decoder.com