Watch now | 🎙️ I ran Opus 5 through my seven-model benchmark, compared it with six other leading models, and came away with a verdict I genuinely didn’t expect ✦ AI generated
The reviewer argues that frontier models have converged in raw intelligence, shifting importance to non-intelligence factors like personality and behavior.
Claire Vo: Why I think we've hit an intelligence overhang and what that means for which model variables actually matter now
provides context · 1
During hands-on testing, Opus 5 displayed a neurotic personality trait, notably refusing to handle a merge conflict in a coding session.
Claire Vo: How Opus 5's 'neurotic' personality showed up in real coding sessions, including a merge conflict it refused to touch
extends · 3
The reviewer posed the same meta-question to both Opus 5 and GPT-5.6 Sol, using their answers as a window into each model's personality traits.
Claire Vo: What I learned from asking both Opus 5 and GPT‑5.6 Sol 'who's smarter, you or me?'
The reviewer describes Opus 5's verbosity — which they call 'Claude Slop' — as a major frustration that makes them angry.
Claire Vo: Claude Slop: the verbosity problem and why it makes my blood boil
extends · 3
The reviewer explains their evaluation methodology: 7 models tested on 6 tasks, scored blindly to produce a leaderboard ranking.
Claire Vo: How the How I AI benchmark works (7 models, 6 tasks, blind scoring)
After testing, the reviewer arrived at a specific plan for when to use Opus 5 versus other models, which surprised them — it is not a straightforward swap.
Claire Vo: My verdict and how I'll actually use Opus 5
extends · 2