Skip to content
aiqbench takeAI Products

aiqbench analysis

JetBrains has launched Mellum2.1, an open-weight Mixture-of-Experts model specifically optimized for software engineering tasks via reinforcement learning on real codebases. The significant jump in SWE-bench Verified scores demonstrates the model's practical efficacy as a coding agent compared to standard LLMs. This release advances the field of specialized AI tools designed to automate complex development workflows.
Source coveringMarkTechPost
What this isA model's reading of the article and related coverage, written for aiqbench. Not the publisher's words.

JetBrains Releases Mellum2.1: A 12B MoE Open Model for Coding Agents

MarkTechPost1 min read

JetBrains released Mellum2.1, an Apache 2.0, 12B mixture-of-experts thinking model with 2.5B active parameters. RL in real repositories lifted its SWE-bench Verified score from 2.0 to 47.0. The post JetBrains Releases Mellum2.1: A 12B MoE Open Model for Coding Agents appeared first on MarkTechPost.

Read the full article at MarkTechPost

Related coverage