Up to date
pngwn CC BY-NC 4.0 out 38 days ago
Verified 2026-10-25 Rank #0 in Decision models · score 0 method v1 Sources 3 Downloads 30d 141 · #616 of 619 tracked
Picked by rule from 2 tracked pieces: the lab's own post, the most shared, a field report, the latest.
TypeSafe AI releases Jev, a System One Model designed for fast, structured automation decisions.
The 1 pick above, plus these 1. Top is the radar's score: discussion, source authority and the lab's own posts, fading with age.
Hugging Face does not say who downloads a model or with what. These are the proxies: API providers listing it, quantized builds, fine-tunes/adapters/merges, and Spaces that load it.
No API provider serves it, so its downloads are people running it themselves: 8 Spaces.
Top Spaces running it: multimodalart/jev-decision-index ♥ 802
Weights, every dated article, and repo commits on one rail.
Teal is the weights (2026-09-17), amber triangles are 2 dated articles (each links to it), grey ticks are repo commits.
Everything else, folded: the full tables, every source.
| Benchmark | Value | Setting / notes | Reported by | Date |
|---|---|---|---|---|
| author-reported ALL | 0.8 | — | model author | 2026-10-07 |
| author-reported ALL | 0.02 | — | model author | 2026-10-07 |
| author-reported ALL | 0.26 | — | model author | 2026-10-07 |
| author-reported choice | 0.63 | — | model author | 2026-10-07 |
| author-reported choice | 0.07 | — | model author | 2026-10-07 |
| author-reported choice | 0.49 | — | model author | 2026-10-07 |
| author-reported escalate | 0.92 | — | model author | 2026-10-07 |
| author-reported escalate | 0.07 | — | model author | 2026-10-07 |
| author-reported escalate | 0.14 | — | model author | 2026-10-07 |
| author-reported noul | 0.94 | — | model author | 2026-10-07 |
| author-reported noul | 0.03 | — | model author | 2026-10-07 |
| author-reported noul | 0.08 | — | model author | 2026-10-07 |
| author-reported review | 0.74 | — | model author | 2026-10-07 |
| author-reported review | 0.05 | — | model author | 2026-10-07 |
| author-reported review | 0.34 | — | model author | 2026-10-07 |
| author-reported severity | 0.75 | — | model author | 2026-10-07 |
| author-reported severity | 0.13 | — | model author | 2026-10-07 |
| author-reported severity | 0.36 | — | model author | 2026-10-07 |
| author-reported team | 1 | — | model author | 2026-10-07 |
| author-reported team | 0 | — | model author | 2026-10-07 |
| author-reported team | 0 | — | model author | 2026-10-07 |
| author-reported workflow4 | 0.84 | — | model author | 2026-10-07 |
| author-reported workflow4 | 0.05 | — | model author | 2026-10-07 |
| author-reported workflow4 | 0.2 | — | model author | 2026-10-07 |
pngwn/system-one-qwen3.5-4b-scorer-v2b is a LoRA adapter based on Qwen/Qwen3.5-4B-Base designed for sequence classification.[1][2] The model scores question options in a single forward pass without autoregressive generation.[3]
Generated 2026-10-07 15:19 UTC by parasail-gemma-4-26b-a4b-it; each numeral points at the fact it rests on. Not a verdict.
Labels are evidence, not verdicts: measured a third-party leaderboard row for this model; author-reported a number the model author published in the card or eval files; structural a deterministic signal from the name, config or chat template, or a decision-model estimate. Each chip links to its source. All use cases.
Listed in Decision models
| Library | peft |
|---|---|
| MoE | no |
| License | CC BY-NC 4.0 (cc-by-nc-4.0) |
| Hub snapshot | 2026-10-25 |
| How it was made | LoRA/adapter fine-tune |
|---|---|
| Lineage bucket | F - fine-tune of an open model (public/synthetic data) |
| Lineage evidence | board file inspection (adapter/head/weight files) + HF base_model field |
| Base model | Qwen/Qwen3.5-4B-Base |
| DI 0.2.1 score | 29.91 (independent (DI 0.2.1 board)) |
| ECE (board) | 0.0589 |
| Median latency | 112.3 ms (DI board, 1x RTX PRO 6000, single process) |
| Hosted price (input) | self-hosted/M |
| Contamination notes | 9,542 contaminated MMLU-Pro test items (in its training data) count as wrong; 5,308 contaminated MMLU test items (in its training data) count as wrong |
| Notes | Board raised a capacity limit ("lifted"). |
| Source | https://huggingface.co/pngwn/system-one-qwen3.5-4b-scorer-v2b |
Base model: Qwen/Qwen3.5-4B-Base
Ranked by source signals (HN, Lobsters, authority domains, official posts) and recency. Summaries are generated from a stored copy of the article text; every sentence cites a span of that text, and nothing is shown that failed the citation check.
Hub snapshot: 2026-10-25 · HF API: 2026-10-24 21:44 UTC · Providers: 2026-10-24 21:44 UTC · Articles: 2026-10-24 21:46 UTC · Summary: 2026-10-07 15:19 UTC · Last verified 2026-10-25
Email alerts are not open yet; the feeds above are the same data. See feeds for the item schema.
