←Story detail

Trending story

SenseTime open-sources SenseNova Loop-9B-Preview

3 reports1 discussions4 story updatesUpdated Nov 1 10:54

Understand this story

AI overview

On October 30, 2026, SenseTime open-sourced the SenseNova Loop-9B-Preview model. According to SenseTime, this is a 9B-parameter Looped Transformer that enhances information flow and reasoning capabilities through parameter-sharing loops and mHC (Manifold-Constrained Hyper-Connections), and the company claims it achieves 27B-level performance on complex tasks. Leiphone reported on October 31 that the model retains the original decoder modules at the first and last 4 layers each, replaces the middle layers with parameter-sharing looped computation modules, and expands the effective computational depth through multiple rounds of iteration. SenseTime claims that the model surpasses Qwen3.5-27B on WorkBuddy Bench, RaccoonPPT Bench, and AutomationBench; in ablation experiments, mHC improved the GPQA Diamond score by 4.42 points and TeamBench by 13.34 points. The model is now available on Hugging Face and GitHub, with plans to later expand to larger models and adaptive fast-and-slow thinking.

AI-generated from public reports

Latest development · Report

SenseTime Open-Sources SenseNova Loop-9B-Preview, Claiming It Rivals 27B-Parameter Models

Developments

1 confirmed developments

  1. SenseTime open-sources SenseNova Loop-9B-Preview

    Source:English text is being prepared.

Reports and discussion timeline

Browse reports and discussion by time. Their evidence levels remain distinct.

Nov 1

  1. English text is being prepared.

    SenseTime Open-Sources SenseNova Loop-9B-Preview, Claiming It Rivals 27B-Parameter Models

    SenseTime announced on October 30 the open-sourcing of SenseNova Loop-9B-Preview. The model adopts a Looped Transformer architecture and expands effective computational depth through recurrent computation; the company claims that at only 9B parameters it can rival 27B-parameter models. The model retains the original decoder modules of 4 layers each at the beginning and end, converts the middle layers into parameter-sharing recurrent computation modules, and introduces mHC (Manifold-Constrained Hyper-Connections) to enhance feature interaction. The company claims that it surpasses Qwen3.5-27B on evaluations such as WorkBuddy Bench, RaccoonPPT Bench, and AutomationBench, and that in ablation experiments GPQA Diamond and TeamBench improved by 4.42 points and 13.34 points, respectively.

  2. IT Home · AIRelated discussion

    IT Home · AI joined this discussion

    This post contributes to heat; it is not a formal report or confirmed fact.

Oct 31

  1. Leiphone

    SenseTime Open-Sources SenseNova Loop-9B-Preview Looped Computation Model

    SenseTime has open-sourced SenseNova Loop-9B-Preview, which adopts the Looped Transformer architecture, retains the original decoder modules of the first and last 4 layers each, and replaces the middle layers with parameter-sharing looped computation modules, expanding the effective computational depth through multiple rounds of iteration and benchmarking against 27B models at the 9B parameter scale. The model introduces mHC (Manifold-Constrained Hyper-Connections) multi-path residual connections to enhance feature interaction; in ablation experiments, GPQA Diamond and TeamBench improved by 4.42 points and 13.34 points, respectively. SenseTime claims that the model outperforms other models in code generation, office scenarios, and agent tasks, and surpasses Qwen3.5-27B on WorkBuddy Bench, RaccoonPPT Bench, and AutomationBench. The model weights have been open-sourced.

Oct 30

  1. SenseTime

    SenseTime Open-Sources the SenseNova Loop-9B-Preview Model

    SenseTime has open-sourced SenseNova Loop-9B-Preview, a 9B Looped Transformer that improves information flow and reasoning capabilities through parameter-sharing loops and mHC (Manifold-Constrained Hyper-Connections). The company claims it achieves 27B-level performance on complex tasks, surpassing Qwen3.5-27B on WorkBuddy Bench, RaccoonPPT Bench, and AutomationBench; mHC improves the GPQA Diamond score by 4.42 points and TeamBench by 13.34 points. The model is now available on Hugging Face and GitHub, with plans to later expand to larger models and adaptive fast/slow thinking.

Heat trend for this story

Current
8
Period peak
15 Nov 1 19:00
24-hour change
—

Move the pointer or select the chart to inspect hourly heat. Use the left and right arrow keys with a keyboard.

Related stories

  1. Related storiesMeta releases open-weight model Muse Spark Open
  2. Related storiesSGLang natively supports and powers the Beam production API
  3. Related storiesStepFun updates Step Code to v0.1.4
  4. Related storiesAnt Ling Open-Sources Medical-Enhanced MoE Model Ling-3.0-flash-Sante