devwithjev
— reading now— views
Submit a build

Comparing Models on ASAP Essays

The repository compares Jev, a decision-model API, gpt-oss-20b, and gpt-5.4-mini on comparative judgment of ASAP essays.

Open source
jobakkjobakk@jobakk
Comparative judgment of ASAP essays by Jev (a decision-model API), gpt-oss-20b and gpt-5.4-mini: code, prompts, judgment logs and results
Oct 3, 2026GitHubView on GitHub
It includes code, prompts, judgment logs, and results.

Also filed under Research & data

  • Compares Jev and Claude on TripAdvisor Rating Extraction

    The project evaluates Jev against Claude for TripAdvisor aspect-rating extraction using HuggingFace data.

  • Jev Deep Research

    Jev Deep Research integrates Jev into a research agent that locates relevant source regions with Choice and Noul, then returns verbatim passages for verification.

  • Jev-Powered Research Paper Radar

    JEV Paper Radar is a scheduled research-paper radar that asks Jev whether each paper matches configured interests and exclusions, then publishes ranked web and feed output.

  • Jev Reranks Knowledge Search Results

    You.com uses Jev through OpenRouter as a reranking layer for Knowledge in its Web Search API, selecting relevant results between retrieval and synthesis. The setup used 3x fewer tokens and achieved 84% accuracy on the Vertical RTK benchmark.