A 3-billion-parameter agent closes in on models ten times its size
Microsoft Research's open-source Orchard framework provides shared infrastructure for agent training. Orchard-SWE scores 69.7 percent on SWE-bench Verified.
Models
Microsoft Research's open-source Orchard framework provides shared infrastructure for agent training. Orchard-SWE scores 69.7 percent on SWE-bench Verified.
Microsoft Research's MindTopo benchmark measures whether multimodal models understand relations like connectivity and knottedness. They do well on static images, not on action.
Microsoft Research's CARE-X combines free-text reporting with calibrated diagnostic scores for chest X-ray interpretation. It is a research model, not a product.