Matthew Berman puts Claude Opus 5.5 through a full test suite: Anthropic went crazy
Matthew Berman · youtube · 2026-09-23
Matthew Berman publishes a video review of Anthropic's newly released Claude Opus 5.5, calling the release evidence that Anthropic "went crazy."
- Joined by guest Thariq, he runs a battery of hands-on tests (coding, reasoning and more)
- The full Opus 5.5 test results are collected in a companion article on Forward Future
- Links to Anthropic's official launch page are included
The video's takeaway is strong praise for the model's capabilities; detailed benchmarks are in the companion review.
Related event: Matthew Berman live-tests Opus 5.5 with Anthropic's Thariq(3 posts)→
More from Models
- ChatGPT UI Confusion: Chat Mode Lacks Astra, Dropdown Shows 'Latest' Instead of GPT-6 — Miles_Brundage · 2026-09-24
- A private eval with a 0% completion rate for 3 years: no AI model can identify this flag — generativist · 2026-09-24
- Contrastive-LM org ships CLM-v0.1-8B model and Nemotron pretraining dataset on HF — _akhaliq · 2026-09-24
- Former OpenAI VP Brundage: ChatGPT web keeps resetting voice from Astra to Sol — Miles_Brundage · 2026-09-24
- Models now generate animated videos from scratch via HTML and Blender faster than predicted — xuanalogue · 2026-09-24
- Opus 5.5's safety classifier refuses to visualize another model's rollouts — eliebakouch · 2026-09-24