lowkeysmile
Re:Step 5 Preview: StepFun's frontier model with 1M context and video ...
on Monday September 21, 2026 @10:16AM (#49787599)
Anyone tried this for actual coding yet? Curious how token-effective it is compared to Kimi K3. The benchmark results looks close but in real-world tasks it may different.
Re:Stepfun Step 5 Preview (LLM): On AA Pareto frontier
on Saturday September 19, 2026 @03:48AM (#49764326)
The price/performance looks interesting, though it also seems pretty verbose. Has anyone actually tried it? How to try it?