AI is happening. The future is updating.IQuest-Q1
**IQuest-Q1** is a Mixture-of-Experts (MoE) model developed by **IQuest** for agentic coding, reasoning, and multi-step tool use. It comprises approximately **320B total parameters**, with an estimated **15B parameters activated per token**. IQuest-Q1 performance across benchmarks. DeepSeek-V4-Flash/Pro refer to the official 0731/0813 releases, respectively. Humanity's Last Exam is reported without tools. IQuest-CLIBench is our in-house benchmark for CLI user experience. For reproducibility, we recommend using a temperature of 1.0, top-p of 0.95, and top-k of 20, with Claude Code `2.1.140` or Codex `0.142` as the respective harness.
**IQuest-Q1** is a Mixture-of-Experts (MoE) model developed by **IQuest** for agentic coding, reasoning, and multi-step tool use. It comprises approximately **320B total parameters**, with an estimated **15B parameters activated per token**. IQuest-Q1 performance across benchmarks. DeepSeek-V4-Flash/Pro refer to the official 0731/0813 releases, respectively. Humanity's Last Exam is reported without tools. IQuest-CLIBench is our in-house benchmark for CLI user experience. For reproducibility, we recommend using a temperature of 1.0, top-p of 0.95, and top-k of 20, with Claude Code `2.1.140` or Codex `0.142` as the respective harness.