We tested NVIDIA NeMo Switchyard’s stage router for coding agents in Ramp SWE-Bench.
100.588 görüntüleme
12 Yorum
Yorumlar X (Twitter) üzerindeki orijinal gönderiden alınmıştır

@RampLabs
Try Switchyard in Ramp Router →
17 beğeni

@hshaiyon
Very cool piece of tech, been great working with the NVIDIA team on this!
13 beğeni

@a_levitator
So nice of Ramp to collaborate with lesser-known AI startups ❤️
10 beğeni

@RyanAmiri__
@JensenHuang woahhhh this is some crazy stuff?!? You seeing this 👀
6 beğeni

@joshuaduniganx
self driving spend management , dream team
5 beğeni

@rene_sultan
Shah of benchmark @hshaiyon 🐐
1 beğeni

@UnderKong
The interesting part is that routing starts turning model choice into an optimization problem, not a product decision.If agents can dynamically pick the cheapest model that still clears the task, the real moat may shift toward orchestration: knowing when to spend frontier-model compute and when not to.
1 beğeni

@stretchcloud
Similar approach in Campfire's agent race mode, but inverted: instead of a pre-defined routing rule, you run multiple coding backends concurrently and pick the best result. Campfire supports 7 backends: Claude Code, Codex, Goose, Aider, OpenHands, OpenClaw, and OpenCode. The cost-cascade variant stops remaining backends the moment the cheapest one completes successfully. If the low-cost backend solves it, the expensive ones never finish. What you get over a fixed router: no need to pre-classify which model handles which task type. The race gives you the answer empirically on each individual problem.

@hussainanjar
Comparable performance at lower cost is exactly the tradeoff teams want.

@kn_neeraj1
@grok what is Nvidia Nemo switchyard?

@jatingargiitk
this is the right move. single-model agents waste tokens on easy stuff and still fail on the hard stuff. curious how you're handling the handoff though — does the router see the full context or just the task description? we kept hitting cases where the cheap model needed expensive-model context to even know it was the wrong model for the job.

@voidhelm_gg
Comparable performance with lower cost is a huge win.