# Jeeves — PostHog's 9B decision model reasons before it picks > An open decision model that writes a reasoning chain first, then returns calibrated probabilities for each option. - Org: PostHog - Date: 2026-09-29 - Category: model, repo - Source: https://github.com/PostHog/jeeves - Canonical page: https://ai-tldr.dev/releases/posthog-jeeves/ ## In short Jeeves is PostHog's open 9B Jev-compatible decision model. It thinks before it answers and scores 0.935 on JevBench's public tiers against Jev's 0.866. Weights, training code and data are MIT-licensed. ## What it is Jeeves is a 9B decision classifier from PostHog that takes Jev's request format — yes/no, multiple-choice and rating questions — and returns a probability for each option. Unlike most Jev-like models it reasons before it decides. The weights are on Hugging Face and the repo ships the full training code and data. ## How it works The model is Qwen3.5-9B with a LoRA adapter and a pointer head that scores each option at a special decide token after the reasoning chain. Training used supervised fine-tuning on 19,126 questions, then CISPO reinforcement learning, then a fitted temperature for calibration. A diffusion drafter adapted to Qwen3.5's Gated DeltaNet layers speeds up the reasoning chain by about 1.6×. ## Why it matters Pipelines often use a Jev-like model for fast, calibrated answers and fall back to a large reasoning model when accuracy matters. Jeeves tries to do both in one self-hosted model: 0.889 on its out-of-domain test split against 0.857 for Jev. The trade-offs are stated plainly — it trails Jev on MMLU (0.793 vs 0.900), and full thinking takes a 3.3 s median on one H100, so answers can be capped or skip thinking. ## Who it's for ML engineers building classification and routing pipelines ## Try it hf download PostHog/jeeves --local-dir jeeves-weights ## Links - [GitHub Repo](https://github.com/PostHog/jeeves) - [Model Weights](https://huggingface.co/PostHog/jeeves) - [HN Discussion](https://news.ycombinator.com/item?id=49891290)