Qwen3.5-9B
Ingenix Claims Top LongevityBench Ranking, Opens Thalamus Model
Polish AI start-up Ingenix says its 9-billion-parameter Thalamus Reasoning model ranks first among 29 systems on LongevityBench, a benchmark for language models in…
Baseten releases mammoth-1 and elephant-1, open-source decision models
Baseten has released two open-source decision models, mammoth-1 (27B) and elephant-1 (9B), trained by its own research lab. According to the company, mammoth-1 ranks #1…
JetBrains releases Mellum2.1, an open 12B model built for coding agents
JetBrains has released Mellum2.1, an updated version of its open-source 12B mixture-of-experts model, aimed at coding agents and fast sub-agents that run on users' own…
Microsoft's Agent Lightning v1.0 Trains Agents With Their Real Harnesses
Microsoft Research Asia has open-sourced Agent Lightning v1.0, a rebuilt reinforcement learning framework of about 3,500 lines of code that lets the same harness used in…
Harness-Zero study trains an agent harness into a small model
Researchers at Peking University trained the behavior of a specialized agent harness into a small model, then removed the harness, and the model outperformed the…