view article Article Darwin-27B-ZTC: A Single-Pass Judge and a Quantitative Look at Its Calibration FINAL-Bench • 4 days ago • 12
view article Article Open Superconductor Challenge: Help Discover the Next 2D Superconductor — From Your Laptop FINAL-Bench • 13 days ago • 12
view article Article Your model already knows it's wrong. Asking costs 0.06 seconds and zero tokens. FINAL-Bench • 21 days ago • 13
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. • 15 items • Updated 2 days ago • 46
view article Article Inside the JEV Ecosystem: 13 Answer Verifiers on One Test Set mayafree • 22 days ago • 12
view article Article OpenRouter Leaderboard: 425 Models by Price, Measured Speed and Korean Quality ginigen-ai • 26 days ago • 13
view article Article Same bytes, closer to the original: two lines of AutoRound we had wrong FINAL-Bench • 28 days ago • 12