News for hackers. Stuff that matters.
Re:Claude Opus 5.5 by felixgallo on Tuesday September 22, 2026 @12:42PM (#49804128)
If you read the page, Opus is now significantly better than Astra while also being cheaper and having more performance headroom available.
Re:Claude Opus 5.5 by abtinf on Tuesday September 22, 2026 @12:50PM (#49804292)
I read the page. It seems like a marginal improvement.
Re:Claude Opus 5.5 by ryanscio on Tuesday September 22, 2026 @12:45PM (#49804198)
Let's wait for independent benchmarks at least
Re:Claude Opus 5.5 by esafak on Tuesday September 22, 2026 @01:17PM (#49804745)
Re:Claude Opus 5.5 by felixgallo on Tuesday September 22, 2026 @12:55PM (#49804389)
the benchmarks provided are already from independent organizations:

Terminal-Bench 4.0 - Stanford & Laude Institute (with funding from all of the AI companies)

FrontierCode v1.1 - Cognition

CursorBench - Cursor (now SolarBoringSpaceXAI I believe)

GDPVal-AA - Artificial Analysis

AutomationBench - Zapier

Humanity's Last Exam - CAIS and Scale AI

Terminal-Bench-Science - Stanford, Laude, Ai2, Allen Institute

OSWOrld - XLANG Lab @ the University of Hong Kong

Chartography - Surge AI

Re:Claude Opus 5.5 by mattz56 on Wednesday September 23, 2026 @07:15AM (#49814310)
Better than Astra looks insane. I saw a Higgsfield video yesterday where they gave the same prompt to Astra and Opus 5.5 to create a samurai video game, and the difference was huge.