TBF, they all believed that scaling reinforcement learning would achieve the next level. They had planned to "war-dial" reasoning "solutions" to generate synthetic datasets which achieved "success" on complex reasoning tasks. This only really produced incremental improvements at the cost of test-time compute.
Now Grok is publicly boasting PhD level reasoning while Surge AI and Scale AI are focusing on high quality datasets curated by actual PhD humans.
In my opinion the major advancements of 2025 have been more efficient models. They have made smaller models much, much better (including MoE models) but have failed to meaningfully push the SoTA on huge models; at least when looking at the USA companies.
You can try to build a monster the size of GPT-4.5, but even if you could actually make the training stable and efficient at this scale, you still would suffer trying to serve it to the users.
Next generation of AI hardware should put them in reach, and I expect that model scale would grow in lockstep with new hardware becoming available.
