Matt Wolfe tests Trinity Large Thinking, an open-source model from RC that matches Opus 4.6 and other top models on benchmarks. He demos fast code generation and multi-step tasks, then pivots to the real problem: nobody has figured out how to build benchmarks that actually measure what matters in real work.
We got a new model out of a company that, well, this is my first time actually hearing about them. They're called RC and they released a model called Trinity Large Thinking. And this is also an open source model released under Apache 2.0. And it's another American company. Taking a look at the benchmarks here, they're comparing it with Opus 4.6, KIMI K 2.5, GLM-5, and Minimax M 2.7. And it seems to be pretty on par with most of those models. They do show it off in use creating a snake game, doing what appears to be some like agentic work, working through through a whole bunch of different steps here. We see it doing some code insanely fast. I don't know if that's real time or not. I gotta be honest with you, really struggle to think of new ways to really test and find ways to prove that these models are getting better. I would love to have like my own benchmark that I'm constantly testing these new models against, but I just don't really have any ideas because my main goal is to show off how these models are useful to the most amount of people, to like everyday use cases in your business and your life. And for the most part, these models are kind of already doing what we need them to do. So there's somebody out there that wants to help me create that benchmark or work with me to help better test these large language models as they come out, hit me up over on X or LinkedIn and, uh, let's chat because I would love to figure out some sort of better way to test and sort of benchmark these models for normal everyday use for people.
AI News: Dots, GPT-6.1 Sol, Sonnet 5.5, Gemini 4, and everything you need to know
