# fstandhartinger/jevbench

> A benchmark for Jev-class decision models: the model receives state and a rubric, returns a typed answer with probabilities. It scores accuracy, calibration, speed, and cost.

- Magnitude: 2.4 out of 10 — Early signal
- Stars: 106 total · +0 stars today, ≈ 17 by evening
- Star trust: star growth looks organic
- Category: Language models · Language: Python · License: MIT · Created: 2026-09-19 · Last push: 2026-09-23
- GitHub: https://github.com/fstandhartinger/jevbench · Page: https://gitnova.dev/en/r/fstandhartinger/jevbench

## Useful for

- Compare your decision model against Jev 1.13.0 and others on a single scale
- Check probability calibration of a model on the 220-task hard set
- Estimate cost and latency per 1000 decisions to choose between API and self-hosted

## Why it’s here

- 0 stars so far today, about 17 expected by the end of the day.
- The spike has held for 3 days in a row — not a one-off blip.
- The repository is 5 days old and already has 106 stars. With less than two weeks of history, there's no usual pace to compare the spike against yet.
- Top new repositories this week: #160.

## Star trust

Star growth looks organic.

Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer.

## Numbers

- Forks: 11
- Issues and pull requests: 66
- Watchers: 1
- Average over the last week: 20 per day
- Usual pace: too little history (under two weeks)
- Stars in the last hour (measured): 1
- Latest release: v1.4.1 (2026-09-23)

## Stars per day, last 12 days (oldest → newest, today is partial)

2026-09-13 … 2026-09-24: 0, 0, 0, 0, 0, 0, 5, 29, 37, 13, 22, 0

## Spotted in now

- Top new repositories this week: #160

## Similar by description

1. **receptron/laya** — 4.2 · Early signal · Language models · TypeScript · +0 stars today, ≈ 47 by evening
   TypeScript wrapper for running the open-source Laya System-1 decision model via ONNX Runtime: takes a state and typed questions, returns answers with calibrated probabilities in one forward pass.
   Full card: https://gitnova.dev/en/r/receptron/laya.md
2. **mizorewww/laya-mlx** — 5.6 · Cooling · Language models · Python · +0 stars today, ≈ 279 by evening
   Native MLX runtime for Laya typed decision models: returns probabilities for choices, scores or truth values without text generation, running locally on Apple Silicon.
   Full card: https://gitnova.dev/en/r/mizorewww/laya-mlx.md
3. **kraayenjon/awesome-jev** — 2.6 · Early signal · Learning & lists · +0 stars today, ≈ 10 by evening
   A curated list of resources for Jev, TypeSafe AI's System One model that returns typed decisions (Choice, Score, Noul) with calibrated probabilities instead of generated text. Aimed at developers integrating Jev into code.
   Full card: https://gitnova.dev/en/r/kraayenjon/awesome-jev.md
4. **mizorewww/laya-coreml** — 4.0 · Cooling · Language models · Python · +0 stars today, ≈ 57 by evening
   Local port of the Laya model to Apple Core ML and Neural Engine: returns typed decisions (choice, score, yes/no) without token generation, with speed and energy benchmarks.
   Full card: https://gitnova.dev/en/r/mizorewww/laya-coreml.md
5. **Zefan-Cai/Open-Jev** — 4.0 · Early signal · Language models · Python · +0 stars today, ≈ 47 by evening
   Open-Jev serves a context, questions and candidate answers to Qwen-based models and returns typed probabilities directly, without autoregressive generation or JSON parsing. It provides LoRA adapters, a scalar decision head and a local…
   Full card: https://gitnova.dev/en/r/Zefan-Cai/Open-Jev.md

---

Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score.
Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast.
Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself.
Data as of 2026-09-24 02:50 UTC, updated every 30 minutes.