Automated README summary
Automatically summarized from the README on 3 Nov 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
A Turkish benchmark of 66 classification-style tasks in the System One request format, built from public Turkish datasets, for comparing Jev, Microsoft-Decision-1, open models and fine-tuned models on accuracy and calibration.
How it uses Jev
Jev is evaluated through TypeSafe's API via `s1bench run jev`. Each task presents a text and lettered Choice/Noul/Score questions; the answer probability is the probability the model gives the option's letter as the next token, with Choice and Noul asked again with reversed options and averaged.
Primitives:choicenoulscore
Technique worth stealing
Read answers as next-token letter probabilities, reverse options and average, and report calibration (log-loss, Brier, temperature-fitted ECE) alongside accuracy.
Try it
`pip install -e .`, `s1bench build`, `s1bench run jev` (needs `TYPESAFE_API_KEY`), then `s1bench score`.
Model judgments from README excerpts
Project signals use repository metadata, an existing summary and the first 700 README characters, not the full project. “Not found” means not detected in that material; it does not establish absence. These are the original judgments with recorded models and dates, not source audits or run results.
Models & evaluation dates
- Inclusion gate
jev-1.14.0- Project signals
jev-1.14.0- Category
jev-1.14.0- Pattern tags
jev-1.14.0
Evidence
These signals use repository metadata, an existing summary and at most 700 cleaned README characters. ≥ 0.60 means reported in that excerpt; ≤ 0.40 means not found there. The middle band is inconclusive. None is a source-code audit or a test result. The runnable-tool question excludes research experiments; the recommendation question asks for a learning shortlist, not a quality verdict.
- Jev is core to the projectFound in material0.70
- Shows a System One patternnot found in the excerpt0.21
- Describes handling uncertaintynot found in the excerpt0.02
- Reports measured numbersnot found in the excerpt0.04
- Is a runnable toolnot found in the excerpt0.06
- Top-10 learning shortlist signalnot found in the excerpt0.18
- Is a replica of the modelnot found in the excerpt0.11
- Solves a common problem (0–2)score on a 0–2 scale0.95 / 2
- About JevFound in material0.99
no-judgment band (0.40–0.60)
no-judgment band (0.40–0.60)
The Jev model and date for each judgment stage are listed above. Card written by DeepSeek V4.1 Flash from the README on 3 Nov 2026.