Automated README summary
Automatically summarized from the README on 21 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
A Python benchmark comparing Jev (TypeSafe's decision model via OpenRouter) against local classical and neural models on SST-2, AG News and UCI Adult, measuring accuracy, calibration, latency and cost.
How it uses Jev
Jev receives serialized task context plus typed questions and returns probabilities over the label set. The harness normalizes Jev's API answers and local predict_proba outputs to one interface before scoring. Prompts are versioned YAML configs, iterated on val only and frozen before test runs.
Primitives:choicescore
Technique worth stealing
Freeze splits and prompts before test, and treat serialization variants as the study variable to quantify the cost of text-native models on tabular data.
Try it
uv sync, add an OpenRouter key to .env, then run `uv run jev-bench suite local` and `uv run jev-bench suite jev`.
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-1.13.0- Project signals
jev-1.13.0- Category
jev-1.13.0- Pattern tags
jev-1.13.0
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 material0.66
- Shows a System One patternnot found in the excerpt0.18
- Describes handling uncertaintynot found in the excerpt0.06
- Reports measured numbersnot found in the excerpt0.15
- Is a runnable toolnot found in the excerpt0.06
- Top-10 learning shortlist signalnot found in the excerpt0.32
- Is a replica of the modelnot found in the excerpt0.04
- Solves a common problem (0–2)score on a 0–2 scale1.02 / 2
- About JevFound in material0.98
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 21 Oct 2026.