@thermalpastor: The scariest thing about Opus 5.5 is that it goes back to fill in the arm realising the lines were dotted.
Summary
The tweet compares Opus 5.5's performance to Astra on a task, noting it performs better but uses 10x more tokens and draws faster.
View Cached Full Text
Cached at: 09/27/26, 09:17 AM
The scariest thing about Opus 5.5 is that it goes back to fill in the arm realising the lines were dotted. https://t.co/66eLm0S8sD
H (@thermalpastor): Performed the same task on Opus 5.5.
Opus 5.5 performed significantly better but used 10x more tokens. Opus also drew 3x faster than Astra.
Similar Articles
@VraserX: Token for token, GPT-6 Astra doesn’t just beat Opus 5.5. It annihilates it. Astra High uses ~12k tokens per task. Opus …
A tweet speculating that GPT-6 Astra achieves 5.5× better token efficiency than Opus 5.5 (~12k vs ~66k tokens per task), and suggesting OpenAI may have a more powerful internal model still unreleased.
@garrytan: Opus 5.5 with Openclaw is strangely smarter and better at completing tasks than with GPT-6 Astra Surprising
Opus 5.5 with Openclaw is described as surprisingly smarter and more effective at tasks compared to GPT-6 Astra.
Opus 5 benchmarks (30.2% on ARC-AGI3!!!)
Opus 5 achieves 30.2% on the ARC-AGI3 benchmark, marking a notable performance improvement.
@theo_the_dev: BREAKING: Opus 5.5 on Medium just CRUSHED GPT-6 Astra Ultra. $21,365 in tokens for @threejs game. Just compare these tw…
A tweet claims that Opus 5.5 outperformed GPT-6 Astra Ultra in a three.js game development scenario, involving significant token costs and compute time, with human involvement.
Opus 5.5 summary: 66.4% Terminal-Bench, ~40% cheaper to run than Opus 5, cache reads down 60%
Opus 5.5, launched by Anthropic, achieves 66.4% on Terminal-Bench, reduces costs by ~40% compared to Opus 5, and features a 1M context window with cache reads down 60%.