FRAMEWIREIndonesiaUpdated Sep 29Live wire
0:00 / 0:00

Sonnet 5.5 is a generational leap 🤯

Sonnet 5 vs Sonnet 5.5 on quadruped physics: • Sonnet 5: Stiff, derpy stick cheetah • Sonnet 5.5: Fluid kinematics & savanna lighting • Easily rivals GPT-6 Astra & Opus 5.5 Anthropic's mid-tier just broke AI.

Web3BitsSep 29
0:00 / 0:00

Claude Sonnet 5.5 ªoµ½B

ESonnet 5‚æ‚è30%ˆȏ㑬‚¢ E1‚‚̍ì‹Ƃ ‚½‚èőå30%ˆÀ‚¢i—¿‹à•\‚͐˜‚¦’u‚«j EŠJ”­‚̕]‰¿ 10.3% ¨ 70.6% E“ü—Í2ƒhƒ‹Eo—Í10ƒhƒ‹^100–œƒg[ƒNƒ“Opus 5.5‚̔¼•ª “‚¢”»’f‚ÍOpusA“úí‚̍ì‹ƂÍSonnet‚ցB

カツSep 29
0:00 / 0:00

Sonnet 5.5 is up on RamenBench, and it absolutely EVICERATES Sonnet 5!

On High effort, it worked for 53min 54sec and used 321k tokens I don't even have to explain how much better it is than previous generation. And I noticed that starting with Opus 5.5, Claude models have

SalenoSep 29
0:00 / 0:00

Sonnet 5.5 built a working clone of Proof, our open-source document editor, from scratch.

It did it at low effort. kieranklaassen uses this as a test for coding models. Before Sonnet 5.5, only three models he’d tested had managed it: • Fable 5 • GPT-6 Astra • Opus 5.5 Opus

Every 📧Sep 296