jevbooks

← All projects

zero-shot-ie-bench

umstek/zero-shot-ie-bench

Benchmark catalog for zero-shot information-extraction and classification systems, including Jev.

Automated README summary

Automatically summarized from the README on 24 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.

What it is

A curated, schema-validated catalog of 60 zero-shot IE and classification systems across 32 families, benched on versioned multilingual suites with append-only run history, generated result tables, a decision board and a try-it UI.

How it uses Jev

The README lists Jev (cloud, jev-1.14.0) as one catalogued system: it answers the 48 mixed classification questions and the 54-text 9-language suite, scored for accuracy, latency and measured cost. The README does not describe how Jev's typed questions are wired into the bench code.

Try it

bun install · bun run check · bun run render · bun run --cwd bench dev doctor

View on GitHub

Start using Jev: API key and your first request →

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 projectnot found in the excerpt0.04
  • Shows a System One patternnot found in the excerpt0.14
  • Describes handling uncertaintynot found in the excerpt0.02
  • Reports measured numbersnot found in the excerpt0.09
  • Is a runnable toolnot found in the excerpt0.38
  • Top-10 learning shortlist signalnot found in the excerpt0.06
  • Is a replica of the modelnot found in the excerpt0.10
  • Solves a common problem (0–2)score on a 0–2 scale1.31 / 2
  • About JevFound in material0.91
Signals
Jev is core to the project0.04Shows a System One pattern0.14Describes handling uncertainty0.02Reports measured numbers0.09Is a runnable tool0.38Top-10 learning shortlist signal0.06Is a replica of the model0.1000.51Solves a common problem (0–2)1.31 / 2012

no-judgment band (0.40–0.60)

Design patterns
Check-up0.2200.51

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 24 Oct 2026.