# Is PAN 2 SOTA?

Pending benchmarks. Announced Nov 10, 2026; no independent results yet.

As of Nov 12, 2026, PAN 2 is pending benchmarks on isitsota: announced Nov 10, 2026, with no independent results on the boards we track yet.

IFM (MBZUAI)'s open foundation world model for physical intelligence. A multimodal LLM (the conceptual reasoning backbone) writes the next world state as a structured, time-grounded description of events, actions and camera motion; a 29B latent diffusion model trained from scratch (the perceptual reasoning backbone) turns that description into a video of up to 20 seconds. Released November 10, 2026 with public weights and training and inference code under Apache License 2.0. Supported in Hugging Face Diffusers and vLLM.

Canonical: https://isitsota.com/m/pan-2
Last updated: 2026-11-10
Tracking since: 2026-11-10

## Announced facts

| Fact | Value |
| --- | --- |
| Lab | IFM (MBZUAI) with Inception42 |
| Announced | Nov 10, 2026 |
| API | Not yet · No public cloud API announced; run locally from the released weights and code |
| Open weights | Published · Public, ungated Hugging Face repo IFM/PAN2 (BF16 diffusion backbone). The Qwen3.5-9B text encoder and Wan 2.2 VAE are downloaded from their own repositories |
| Parameters | 29B-parameter MMDiT perceptual reasoning backbone, trained from scratch. Conceptual reasoning is a pre-trained multimodal LLM (Kimi K3 is used in the technical report unless stated otherwise). Frozen text encoder is Qwen3.5-9B; VAE is Wan 2.2, both used unmodified from their authors |
| Type | General-purpose world model with Generative Latent Prediction (GLP): conceptual reasoning by a multimodal LLM plus perceptual reasoning by a 29B latent diffusion model (IFM page, model card and GitHub) |
| Output | Video via the Wan 2.2 VAE decoder, 704×1248 at 24 fps, up to 20 seconds; text-to-video and image-to-video from one diffusion checkpoint (model card) |
| License | PAN 2 code and weights Apache License 2.0 (IFM announcement, model card and GitHub). Third-party Wan 2.2, Qwen3.5-9B and Diffusers components keep their own licenses |
| Code | https://github.com/ifm-ai/PAN2 (training and inference code; also Diffusers, vLLM and FastVideo) |
| Related | Separate from earlier PAN, from Jais 3 (same lab), and from the frozen Wan 2.2 VAE and Qwen3.5-9B encoder used as components |

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: on 100 egocentric everyday multi-step tasks posed as I2V and T2V (200 prompts, 456 steps), with Kimi K3 as the conceptual reasoner, PAN 2 records 75.10 ± 1.51% step completion and 34.00 ± 3.61% full-plan completion, mean ± SD over 3 seeds (IFM technical report figure on the Hugging Face model card).
- Lab claim: six-capability overall accuracy of 84.48 ± 0.08% (physical consistency, causal coherence, entity persistence, constraint satisfaction, viewpoint control and external dynamism; 300 single-action test cases; IFM technical report figure on the Hugging Face model card).
- Lab claim: Physics-IQ Verified (I2V) 49.38 ± 0.64 in the public leaderboard setting, with Claude Opus 5.5 as the conceptual reasoner, mean ± SD over seeds 123–126 (IFM technical report figure on the Hugging Face model card).

## Sources

- LAB: [IFM on X: Introducing PAN 2](https://x.com/IFM_AI/status/2120199814696828942) (2026-11-10)
- LAB: [IFM on X: PAN 2 weights, training and inference code under Apache 2.0](https://x.com/IFM_AI/status/2120199815724507276) (2026-11-10)
- LAB: [IFM PAN 2 page](https://ifm.ai/pan/) (2026-11-10)
- REPO: [IFM/PAN2 on Hugging Face](https://huggingface.co/IFM/PAN2)
- REPO: [ifm-ai/PAN2 on GitHub](https://github.com/ifm-ai/PAN2)

Tracking continues until an independent board lists it.

## Related

- Lab: [IFM (MBZUAI) with Inception42](https://isitsota.com/labs/mbzuai-ifm.md)
- All pending releases: https://isitsota.com/releases.md
- JSON: https://api.isitsota.com/v1/models/pan-2