A repost claims Anthropic’s Opus 5 regresses badly despite benchmark gains
rickasaurus · x · 2026-07-28
A repost of an article argues that Anthropic’s Opus 5 feels like a bad model after a few hours of use.
The author claims the model may have improved in some areas, but says its benchmark results look like “fraud” and that several behaviors have regressed badly in practice.
More from Models
- Claude Code creator says startups should chase the model capabilities nobody has productized yet — ycombinator · 2026-07-28
- Kimi K3 arrives on Applied Compute for training and inference — rhythmrg · 2026-07-28
- Polymarket prices a 76% chance Moonshot ships another Kimi K model by September — Polymarket · 2026-07-28
- The Verge says Moonshot’s open Kimi K3 could undercut closed U.S. AI models — The Verge AI · 2026-07-28
- Kimi K3 lands on Fireworks AI for inference and training — omarsar0 · 2026-07-28
- Gemini video generation adds words and blocks some harmless prompts — Individual-Cookie615 · 2026-07-28