Claire Vo · 2 min read · Gen AI Tools
Claude Opus 5 review: this model is brilliant (but annoying)
Read the original on lennysnewsletter.com →
This hands-on Opus 5 review covers personality analysis, live benchmark results from a 7-model evaluation, and a practical verdict on whether to adopt it. It discusses the idea of an intelligence overhang, how Opus 5’s “neurotic” personality affected real coding tasks, and how it stacks up against GPT‑5.6 Sol, Sonnet 5, and Gemini 3.1 Pro, including a standout use case where it performed exceptionally.
Key Takeaways
- There’s an emerging intelligence overhang that reshapes which model variables actually matter.
- Opus 5’s “neurotic” personality affected real coding tasks, including a merge conflict it wouldn’t touch, influencing usability.
- Live benchmarks and leaderboard results show how Opus 5 compares to GPT‑5.6 Sol, Sonnet 5, and Gemini 3.1 Pro.
- There is at least one use case where Opus 5 earned straight 5s, informing practical adoption decisions.
Excerpt
I’m tired of new models. Every week there’s a new benchmark, a new frontier intelligence claim, a new thing to test. But here we are, because Opus 5 just dropped and I’ve had real hands-on time with it, so you’re getting the honest version. This is my full Opus 5 review: personality analysis, live benchmark results from my 7-model How I AI eval, and an actual verdict on whether I’m swapping it in. Spoiler: the answer surprised me. Listen or watch on YouTube , Spotify , or Apple Podcasts What you’ll learn: Why I think we’ve hit an intelligence overhang…