ModelScope· ModelScope2022· Published Sep 29, 6:00 AM ET· added Oct 8, 8:43 PM ET54/100AI score54/100

IQuest-Q1 released as 320B MoE model for long-horizon coding agents

Original titleIQuest-Q1 lands with 320B MoE scale, 15B active parameters, and a 512K context window for long-horizon coding agents.

AISummary

ModelScope announced IQuest-Q1, a 320B MoE model with 15B active parameters and a 512K context window for agentic coding. The post reports scores of 84.5 on CyberGym, 83.2 on Terminal-Bench 2.1, 64.6 on DeepSWE v1.1, and 63.0 on NL2Repo, and says weights are released under the IQuest-Q1 License.

Read the original x.com

Source: ModelScope · x.comPublished Sep 29, 6:00 AM ET · added here Oct 8, 8:43 PM ET

AI agents AI coding Reasoning Open-source ecosystem Model releases Evals & benchmarks #Model release #Agent #Coding #Eval/Benchmark