Claude Opus 5 Achieves Leading Scores Across AI Benchmarks
Anthropic's latest model outperforms prior versions on agentic coding and knowledge tasks.
Introducing Claude Opus 5. It's a thoughtful and proactive model that comes close to the frontier intelligence of Fable 5 at half the price.
Reactions
28 postsJM 
Jack Morris@jxmnopAwesome new addition to my workflow. for complex reasoning, ill reach for Opus 5 medium, thats assuming Sonnet-5 or Gpt-5.6 Luna can't do the job. if it's deep knowledge work, still don't see a better option than Fable low. for complex systems engineering, i dont trust anythingโฆ
- likes: 300
- replies: 21
- bookmarks: 153
- reposts: 11
T( Teortaxesโถ๏ธ (DeepSeek ๆจ็น๐้็ฒ 2023 โ โ)@teortaxesTexOpenAI is still just much more efficient in hardcore reasoning https://twitter.com/ArtificialAnlys/status/2080734447717298483
- likes: 209
- replies: 8
- bookmarks: 27
- reposts: 6
AA Artificial Analysis@ArtificialAnlysClaude Opus 5 is the new leader on our agentic knowledge work benchmark, AA-Briefcase, outperforming Claude Fable 5 by nearly 150 Elo while reducing Cost per Task by 20% @AnthropicAI has released Claude Opus 5, the new leader on the Artificial Analysis Intelligence Index, andโฆ
- likes: 628
- replies: 27
- bookmarks: 78
- reposts: 62
AA Artificial Analysis@ArtificialAnlysClaude Opus 5 offers a wide range of intelligence-cost tradeoffs across its five effort settings. Max effort costs $17.79 per task, around 20% less than Claude Fable 5 ($22.30) while achieving a higher AA-Briefcase Elo. Notably, Claude Opus 5 with high effort outperforms Claudeโฆ
- likes: 46
- replies: 1
- bookmarks: 3
- reposts: 4
AA Artificial Analysis@ArtificialAnlysAA-Briefcase measures performance across objective rubric criteria, analytical quality, and presentation quality. Claude Opus 5โs gains are driven primarily by rubric pass rate and analytical quality. At max effort it achieves an Analytical Quality Elo of 2016, nearly 300 Eloโฆ
- likes: 41
- replies: 1
- bookmarks: 2
- reposts: 2
AA Artificial Analysis@ArtificialAnlysClaude Opus 5โs top three effort settings all average more than 25 minutes per AA-Briefcase task (36.2, 34.3, and 25.7 minutes for max, xhigh, and high). At max effort this is roughly 50% longer than Opus 4.8 (24.1 minutes), primarily due to an increase in the number of turns.โฆ
- likes: 22
- replies: 2
- bookmarks: 2
- reposts: 1