{"type":"post","id":"the-platform-for-inference-training-and-execution-896444","slug":"the-platform-for-inference-training-and-execution-896444","title":"The platform for inference, training, and execution","description":"Baseten says Genspark post-trained the open Qwen3.5-397B model for its Deep Research agent, raising its score on Genspark’s grader from 0.612 to 0.759.","retrieval_nugget":"Baseten says Genspark post-trained the open Qwen3.5-397B model for its Deep Research agent, raising its score on Genspark’s grader from 0.612 to 0.759. The result matters to builders because the partners describe a production deployment and a training process that treats research and report writing as distinct tasks.","published_at":"2026-11-11","updated_at":"2026-11-11","record_date":"2026-11-11","date_kind":"published_at","topics":["inference"],"entities":["Baseten","Genspark","Qwen3.5-397B","Opus 5.5","Sonnet 5.5","GPT-5.6 Sol","DeepSeek V4 Pro"],"related_patterns":["ai-engineering-evaluations-are-splitting-into-task-specific"],"novelty_label":"new_fact","what_changed":"Baseten and Genspark report a post-trained Qwen3.5-397B deep-research model scoring above several leading models, including Opus 5.5.","prior_refs":[],"source_url":"https://www.baseten.co/blog/how-baseten-and-genspark-trained-a-research-model-to-outperform-opus","source_urls":["https://www.baseten.co/blog/how-baseten-and-genspark-trained-a-research-model-to-outperform-opus"],"schema_version":"newruntime-agent-readable-v0.2","stable_id":"post:the-platform-for-inference-training-and-execution-896444","status":"published","visuals":[],"editor":{"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]},"routes":{"html":"https://newruntime.com/posts/the-platform-for-inference-training-and-execution-896444/","markdown":"https://newruntime.com/posts/the-platform-for-inference-training-and-execution-896444.md","json":"https://newruntime.com/posts/the-platform-for-inference-training-and-execution-896444.json"},"markdown_url":"https://newruntime.com/posts/the-platform-for-inference-training-and-execution-896444.md","next_reads":[{"type":"topic","path":"/topics/inference/","url":"https://newruntime.com/topics/inference/","title":"Inference","reason":"Explore the inference topic hub.","media_type":"text/html","markdown_url":"https://newruntime.com/topics/inference.md","json_url":"https://newruntime.com/topics/inference.json"},{"type":"collection","path":"/posts/","url":"https://newruntime.com/posts/","title":"Field Notes","reason":"Open the latest editorial analysis.","media_type":"text/html","json_url":"https://newruntime.com/posts.json"},{"type":"collection","path":"/sources/","url":"https://newruntime.com/sources/","title":"Sources","reason":"See the original sources this archive cites.","media_type":"text/html"}]}