Step 5 Preview: StepFun's frontier model with 1M context and video input

Step 5 Preview: StepFun's frontier model with 1M context and video input(platform.stepfun.ai)

2 points by AnneWodell 17 days ago | 1 comment

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.

lowkeysmile 17 days ago |

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.