IQuest-Q1: Advancing Foundation Capabilities for Agentic CLI Systems
IQuest
An open-source sparse mixture-of-experts agentic foundation model with 320B total and 15B activated parameters, trained for command-line agent work through a three-stage pretraining/mid-training/post-training pipeline with domain-specific RL, multi-teacher on-policy distillation and model merging. It reports SWE-bench Multilingual 80.3, SWE-Bench Pro 57.5, LiveCodeBench v6 89.7, GPQA Diamond 93.3 and Humanity's Last Exam 39.2 without tools (55.7 with).
Why it matters
A 15B-activated open-weight model posting frontier-level agentic coding and science scores puts serious CLI-agent capability outside the closed labs.
Importance: 3/5
open-weight model with frontier-level agentic coding scores