Research & data

I just had to explore using Jev with my existing Japanese print metadata extraction pipeline (where I use gpt-5.6 luna). Turns out that in some cases I could replace luna completely and save a bunch of money - in others I could augment what I had for higher quality! https://t.co/iSFOGPJjf8

Charts: TypeSafe Jev evaluated on Thai standardized exams vs 110 other models.

Jev (TypeSafe) 性能評価プロジェクト — 日本郵便 KEN_ALL をマスタに、AI SDK 経由の Jev が住所のあいまい一致にどこまで使えるかを検証.

TypeScript experiments, evaluations, and latency benchmarks for TypeSafe's Jev model.

Typed-decision benchmark from PadFlow (land development SaaS): schemas, anonymized labeled rows, and a runner for confidence-calibrated models like TypeSafe Jev.

AI benchmark on Japan's 2026 Common Test: Jev vs luna-none vs luna-low (static dashboard).

Benchmarking Jev (Typesafe.ai) against a strong LLM on the Who&When Pro agent-failure-attribution benchmark (text subset).

Jev (TypeSafe) vs Claude Haiku 4.5 on 2 000 phishing emails: accuracy, calibration, latency, cost. Reproducible benchmark.

Can a decision model beat dedicated rerankers? TypeSafe Jev vs Cohere Rerank 4 vs ZeroEntropy zerank-2 vs a chat-model baseline: 14 datasets, every raw API response, bootstrap ranges on every gap.

Independent Jev 1.13.0 behavior study: report, controlled prompt experiments, raw results, and offline verification.

High-throughput synthetic & pretraining dataset sifter powered by TypeSafe AI Jev (api.typesafe.ai). Stream, filter, and score Parquet & JSONL datasets at 1,500+ rows/sec using System One typed decisions (Choice, Score, Noul).

Does a TypeSafe Jev rerank beat embedding search? Graded relevance eval (9,831 pairs, 164 zh/en queries) over the Agent Skills Hub catalog, with the judge-circularity bias measured.

Reproducible early-access evaluation of Jev on Korean understanding and medical text, with runtime and cost evidence.

Local bilingual probability decisions from context, questions, and candidate answers. Independent research preview inspired by TypeSafe Jev.

Unofficial study: Jev-style parallel typed decisions on stock 1.5B-8B models on an Apple Silicon laptop. Benchmarks, research notes, and a Hugging Face Space demo.

Mini-Jev: what a Jev-style typed-decision interface looks like on a frozen Qwen3-4B — read the option letter's logits instead of generating JSON. Preregistered experiment, results, teaching bench.