# Is SenseNova-Loop-9B-Preview SOTA?

Pending benchmarks. Announced Oct 30, 2026; no independent results yet.

As of Nov 3, 2026, SenseNova-Loop-9B-Preview is pending benchmarks on isitsota: announced Oct 30, 2026, with no independent results on the boards we track yet.

SenseTime's open-weights looped multimodal model for long-context and agentic work. Of its 32 decoder layers, layers 4–27 run twice with shared weights (56 layer passes per token), and two-stream Manifold-Constrained Hyper-Connections (mHC) route information between passes. Takes text and images, returns text. Weights on Hugging Face under Apache-2.0; a preview, with the technical report still to come.

Canonical: https://isitsota.com/m/sensenova-loop-9b-preview
Last updated: 2026-10-30
Tracking since: 2026-10-30

## Announced facts

| Fact | Value |
| --- | --- |
| Lab | SenseTime |
| Announced | Oct 30, 2026 |
| API | Not yet |
| Open weights | Hugging Face (sensenova/SenseNova-Loop-9B-Preview, first published as SenseNova-6.8-Loop-9B-Preview) |
| Parameters | About 9.66B stored (9,656,250,480); SenseTime cites ~9B total and ~14.6B inference parameters with the loop |
| Type | Looped (parameter-shared) transformer, image-text-to-text; custom code (trust_remote_code) |
| Loop | 32 distinct decoder layers; layers 4–27 (24 layers) run twice with shared weights, 56 layer executions per forward pass |
| mHC | Two-stream Manifold-Constrained Hyper-Connections with Sinkhorn normalization (20 iterations) |
| Attention | Hybrid: 3 linear-attention layers then 1 full-attention layer in each group of 4 |
| Dimensions | Hidden 4,096; FFN 12,288; 16 attention heads, 4 KV heads; 248,320-token vocabulary; Qwen3.5-style text config |
| Context | Trained at up to 262,144 tokens |
| Checkpoint | 38.1 GB; safetensors list 9.41B F32 and 0.24B BF16 parameters, while the card describes a BF16 backbone with FP32 mHC routing |
| License | Apache-2.0 |
| Serving | LightLLM; SGLang support in an open pull request; fine-tuning via OpenSenseNova/torchtitan |
| Status | Preview; technical report TBD; MTP heads available, Dspark and Dflash2 still training |

Tags marked unsure are not stated on the lab's own pages.

## What would let us call it

Verdicts use only independent boards we already track. Two consecutive snapshots are required before any crown.

- [x] Publicly announced with a source
- [x] Usable by the public (API or weights)
- [ ] Listed on an independent board we track
- [ ] Enough results for a rank in a category
- [ ] Holds across two snapshots (crowns only)

## What the lab claims

Self-reported. Shown for context; not used in any verdict.

- Lab claim: 71.38 on BIRD-Dev, 66.89 on WorkBuddy Bench, 58.87 on AIDABench, 48.89 on TeamBench, 40.45 on Terminal Bench 2.1, 18.56 on τ³-Banking, 13.72 on AutomationBench and 70.70 on RaccoonPPTBench (SenseTime's internal benchmark), from the model card chart.
- Lab claim: ahead of Qwen3.5-27B on WorkBuddy Bench, RaccoonPPT Bench and AutomationBench.
- Lab claim: mHC adds 4.42 points on GPQA Diamond and 13.34 on TeamBench.

## Sources

- REPO: [sensenova/SenseNova-Loop-9B-Preview on Hugging Face](https://huggingface.co/sensenova/SenseNova-Loop-9B-Preview) (2026-10-30)
- REPO: [OpenSenseNova/SenseNova-Loop on GitHub](https://github.com/OpenSenseNova/SenseNova-Loop) (2026-10-30)
- LAB: [SenseTime on X](https://x.com/SenseTime_AI/status/2116151078219858346) (2026-10-30)

Tracking continues until an independent board lists it.

## Related

- Lab: [SenseTime](https://isitsota.com/labs/sensetime.md)
- All pending releases: https://isitsota.com/releases.md
- JSON: https://api.isitsota.com/v1/models/sensenova-loop-9b-preview