ZMIME

Agnes Video H3 MoE vs PAN 2

Compare documented capabilities and access. A dash means a comparable figure is unavailable.

Model specifications
SpecificationAgnes Video H3 MoEAgnes AIPAN 2MBZUAI Institute of Foundation Models
TaskAudiovisual generationWorld simulation
Published capabilitiesExperimental MiniMax H3 FL2VA adaptation that replaces selected feed-forward layers with routed sparse experts.Predicts what happens after an action in a starting scene.
AccessPublic composite package with original weights, learned router and adapter, and reference loaderPublic weights, full training code and inference code
ResultVideo with synchronized audioSimulated video conditioned on a scene and action
Operating limitsSupports an initial frame, an ending frame or both with the publisher’s reference loader.Not published
SourcesModel weightsPublisher documentation
InputsText, ImagesText, Images
WeightsOpen weights · MiniMax H3 Community LicenseOpen weights · Apache-2.0
ReleasedNov 20, 2026Nov 10, 2026