Darwin Family: MRI-Trust-Weighted Evolutionary Merging for Training-Free Scaling of Language-Model Reasoning Paper • 2605.14386 • Published May 14 • 53
view article Article Your model already knows it's wrong. Asking costs 0.06 seconds and zero tokens. FINAL-Bench • 10 days ago • 12
ZTC Models: JEV ecosystems Collection Answer verification from one forward pass, zero generated tokens. Measured against JEV and 10 others on 2,018 identical items. • 10 items • Updated 1 day ago • 44
Running Featured 345 Jev Decision Index 🔬 345 Benchmarks and news on various repros of TypeSafe's Jev
Running Agents 43 Typed Decision Leaderboard 🎯 43 JEV & open-Jev answer verifiers, one identical test set
Running on Zero Agents Featured 256 Laya Demo 🎯 256 Fast System 1 decisions with calibrated probabilities
Running on Zero Agents 317 Qwen-Image-2.1 🎨 317 Generate or edit images with AI from text and photos
Nomic Embed Collection Open Source Long Context Text Embedders • 8 items • Updated Feb 14, 2024 • 25
Nomic Embed: Training a Reproducible Long Context Text Embedder Paper • 2402.01613 • Published Feb 2, 2024 • 19