StateM: Reaching 95.3% Raw Accuracy, or a \$15 Frontier Run, on Terminal-Bench 2.1 via Harness Scaling Paper • 2608.15089 • Published 5 days ago • 223
Running 58 Open Discovery Challenge 🧬 58 Neglected-disease drug leaderboard for AI-designed molecules
Running on Zero Agents Featured 39 GEPARD 🐆 39 Spotted text-to-speech with voice cloning and text-CFG
Running on CPU Upgrade Agents 2.4k Omni Image Editor 🖼 2.4k Image edit, text to image, image upscale, remove watermark
F2LLM Technical Report: Matching SOTA Embedding Performance with 6 Million Open-Source Data Paper • 2510.02294 • Published Oct 2, 2025 • 48