Community project / Evaluations and independent research

RSI-Jev

Jev-like 2B open model trained by a recursively self-improving AI research system, with published version notes including failed experiments (MIT code, Apache-2.0 weights); it returns choice, score, and noul probabilities through a /v1/systemone-compatible server. Its authors report 0.791 on typed-decisions after training on that benchmark's train split and 0.774 on 873 held-out scienthoon tickets; MMLU-Pro remains a weakness at 0.383 on a 1,000-question subset.

Open the original resource ↗ See it in the full directory Start a reading list → Browse all Evaluations and independent research

Download share card ↓

This is an independent community listing. Check the source, license, data handling, and evaluation caveats before relying on a project. Inclusion is not an endorsement or security review.

Found an outdated or inaccurate detail? Report a correction →

Explore more in Evaluations and independent research

• 

  ruling

  MIT-licensed System One-compatible server for Apple Silicon that scores typed questions from a stock model's logits with no training, accepts the official SDK unchanged, and re-scores the 256 public judgments that carry Jev's own answers (231 vs 238, no significant difference); serves MLX checkpoints or any OpenAI-compatible endpoint, with no native CUDA path.

  Read listing →
• 

  SemIf (formerly OpenJev)

  Independent open-model research baseline for direct typed option scoring; it reproduces the interface pattern, not Jev's undisclosed model or training.

  Read listing →
• 

  Simple Jev

  Apache-licensed local server that scores Choice, Score, and Noul with open-model logits; tokenizer support and decision calibration vary by model.

  Read listing →