← Wednesday, September 30, 2026Models & trainingBenchmark

Jeeves reports higher decision accuracy than Jev-like baselines on held-out data

github.com 7 min read Editor score 8/10

Jeeves combines a fine-tuned 9B model, a pointer head and a diffusion drafter, reporting 0.889 accuracy on unseen test data and 0.935 on JevBench public tiers; code and data are available. Its results and latency figures give engineers a concrete basis for evaluating reasoning-based decision models.

What

Jeeves is a 9B Jev-like classifier that reasons before deciding, built from Qwen3.5-9B with LoRA, a pointer head, and a block-4 diffusion drafter.

How

Trained with CISPO, it scores 0.889 on held-out test data versus 0.822 for Kev-9B and 0.857 for Jev; thinking lifts its score from 0.804 to 0.840.

Why it matters

Its Jev-compatible API handles yes/no, multiple-choice, and rating questions in one request, offering a reasoning-based alternative to fallback pipelines.

Read on github.com → Hacker News · 89 comments

Headline, summary, brief and diagram are written by a model from the source's own text; the link, byline and numbers come from the source. Read the original before relying on a claim.