Claude Opus 4.1
AnthropicCoding model2 posts
Every Claude Opus 4.1 comparison on aivs.tv: 1 side-by-side post from X against other models on the same prompt, plus 1 solo run on classic topics, 2 with cost or time reported. Compare coding ability, cost and speed from real tests.
Posts
2incl. 1 solo run
Summary
Claude Opus 4.1 (Anthropic) appears in 2 posts on aivs.tv, next to GPT-5. Tasks: one-shot GTA and next.js customer feedback app. Reported for Claude Opus 4.1: 2 min in @chetaslua's one-shot GTA and 33K tokens in @iannuttall's next.js customer feedback app. @iannuttall picks Claude Opus 4.1 as the best result in next.js customer feedback app.
What each post reports for Claude Opus 4.1
| Post | Time | Cost | Tokens | Author’s verdict | Original |
|---|---|---|---|---|---|
| One-shot GTA@chetaslua | 2 min | — | — | — | X post |
| Next.js customer feedback app@iannuttall | — | — | 33,000 | Author’s pick | X post |
Only numbers stated in each post. “—” means the post doesn’t say.
Who won where
1- Next.js customer feedback app“Opus is still the more capable model out of the box and Claude Code is the more complete CLI product”— the author’s view, @iannuttall
Matchups with Claude Opus 4.1
1Spellings we map to Claude Opus 4.1
“Opus 4.1”, “Opus4.1”