Opus 5 is currently #1 on Artificial Analysis Intelligence Leaderboard

	Opus 5 is currently #1 on Artificial Analysis Intelligence Leaderboard(artificialanalysis.ai)
	319 points by aarondong 16 hours ago \| 180 comments
	tl;dr: Anthropic's Claude Opus 5 has taken the top spot on Artificial Analysis's Intelligence Index v4.1, which aggregates nine benchmarks including GDPval-AA v2, Terminal-Bench v2.1, SciCode, Humanity's Last Exam, and GPQA Diamond. The leaderboard also tracks cost per task, output speed, latency, token usage, and context window size across proprietary and open-weight models.
	HN Discussion: ↑Confirms Opus 5's superiority by highlighting it outperforms competitors even at lower effort settings ↓Cost-effectiveness undermines the ranking since cheaper models match Opus 5's performance ↓Claude's censorship and safeguards make its top ranking practically meaningless for real use ↑Personal user experience praising Opus 5's improved behavior over previous models ~Benchmarks are incomplete without testing long-context performance with irrelevant filler