GPT-6.1 Terra vs Claude Opus 5.5: Same Prompt, Not Even Close
MattVidPro · youtube · 2026-10-27
MattVidPro tests OpenAI's new GPT-6.1 Terra (the mid-tier model between Luna and Sol, priced at half of Sol) against Claude Opus 5.5 with one prompt: a diecast RX-7 with an animated Wankel engine plus five reference photos.
- The OpenAI models (Terra Light/High, Sol Medium) all needed a "3d pls" follow-up to produce 3D output; Claude nailed it in one shot with no hints
- The video also covers pricing across Luna/Terra/Sol/Astra, whether Terra's benchmarks justify the price, and OpenAI's three newly announced math and physics results
- Author caveats: single test, single prompt — try it yourself
More from Models
- UC Berkeley paper: RL reweights LLM reasoning strategies rather than expanding them — burny_tech · 2026-10-27
- Artificial Analysis launches AA-3D Explorer to compare model-built 3D scenes in your browser — ArtificialAnlys · 2026-10-27
- ChatGPT keeps rejecting innocent game-art prompts as 'harassment and bullying' — AnonymousForALittle · 2026-10-27
- Qwen3.5-4B Fine-tune Specialized in Three.js 3D Code Trends on Hugging Face — ccore · 2026-10-27
- Steering vectors turn Qwen3.5-4B into "Golden Gate Qwen" with a known recipe — burny_tech · 2026-10-27
- Experiment finds 9 'gender neurons' in Qwen3.5-4B that flip its self-identity — burny_tech · 2026-10-27