• Chenet et al claim behavioural test success equals AGI, but authors dispute this. • Statistical approximation alone cannot demonstrate general intelligence, as it lacks causal reasoning. • Three key objections: lack of causal understanding, overfitting to test patterns, and absence of flexible reasoning. • Behavioural tests may reward pattern matching, not true cognition, leading to misleading AGI claims. • The debate highlights limits of current AI evaluation metrics, urging more robust benchmarks. • Calls for theory-driven, interdisciplinary approaches to truly assess general intelligence.

Article Summaries:

    • CORRESPONDENCE Statistical approximation is not general intelligence Access options Access Nature and 54 other Nature Portfolio journals Get Nature+, our best-value online-access subscription 27,99 € / 30 days cancel any time Subscribe to this journal Receive 51 print issues and online access 185,98 € per year only 3,65 € per issue Rent or buy this article Prices vary by article type from$1.95 to$39.95 Prices may be subject to local taxes which are calculated during checkout Nature 650, 792 (2026) doi: https://doi.org/10.1038/d41586-026-00495-y Competing Interests The authors declare no comp

Sources: