Concrete Data Proving AI's Decline in Intelligence: Claude Opus 4.5 This data shows the Marginlab team using Claude Code's Opus 4.5 daily to perform pass/fail tests on 50 questions in the SWE-Bench-Pro test. The data shows that the pass/fail rate has dropped from 60% in early January to 54% currently. The rate of AI decline is 10%.
Risk and Disclaimer:The content shared by the author represents only their personal views and does not reflect the position of CoinWorldNet (币界网). CoinWorldNet does not guarantee the truthfulness, accuracy, or originality of the content. This article does not constitute an offer, solicitation, invitation, recommendation, or advice to buy or sell any investment products or make any investment decisions
No Comments
edit
comment
collection25
like31
share