Mubit open-sources Banyan Sapling, a verification model with calibrated probabilities (Apache 2.0)
testingcatalog · x · 2026-10-24
Mubit released Banyan Sapling, an Apache 2.0 research-preview model focused on verification: given context, it judges whether a claim is supported, violated, missing information, or contradicted — with calibrated probabilities. On its own eval of 1,731 cases it answered 779 confidently and abstained on the rest. It's the first of the Banyan family, tied to Mubit's agentic runtime calibration platform that captures traces and outcomes to build a dedicated model per repeated agent task, without replacing your frontier models.
More from coding & agent
- Screenshot shows multi-agent AI team with a Chief of Staff that self-corrects — RachelVT42 · 2026-10-24
- This all-in-one ESP32 pocket dev board is programmable by Codex and fits on a keychain — thesephist · 2026-10-24
- Security veteran: 0day patch windows are now hours, security debt interest just spiked — xeophon · 2026-10-24
- Hermes Watch: Open-source agent runs voice Q&A on an Amazfit smartwatch — Teknium · 2026-10-24
- Bug Hunt Bench: blind-graded leaderboard pits frontier coding models against 105 real planted bugs — PawelHuryn · 2026-10-24
- OpenAI Dots now drive on-machine sessions without spawning new Codex sessions — brandon_galang · 2026-10-24