MODEL Microsoft Last updated:

MatterGen

Generative Materials Discovery

Microsoft's January 2025 generative model for inorganic materials — generates novel crystal structures with target properties (band gap, magnetism, ionic conductivity). Published in Nature. Combined with Microsoft's MatterSim (property simulator), forms a closed-loop materials design system. Used by partners in battery, semiconductor, and catalyst R&D.

Cost
Free
Open weights — self-host
How are Intelligence, Speed & Cost bucketed?
Intelligence and Speed buckets are percentile ranks on Artificial Analysis. Cost buckets are fixed dollar thresholds keyed off output-token price ($/M out).
Intelligence
  • Top 1%≤ 1%
  • Top 5%≤ 5%
  • Top 10%≤ 10%
  • Good≤ 25%
  • Medium≤ 50%
  • Below avg> 50%
Speed
  • Top 1%≥ 345 tok/s
  • Top 5%≥ 237 tok/s
  • Top 10%≥ 196 tok/s
  • Good≥ 146 tok/s
  • Medium≥ 90 tok/s
  • Slow< 90 tok/s
Cost
  • Freeopen weights · self-host
  • Low< $1 / M out
  • Moderate$1–5 / M out
  • High≥ $5 / M out

Why it matters

Made generative materials discovery a real workflow rather than a research demo. Combined with Orbital Materials, NVIDIA BioNeMo, and academic Boltz / RFdiffusion, AI-for-materials is now an investment category.

Core Capabilities

Science
Built for biology, chemistry, materials, weather, or math research.
Generative
Produces images, video, audio, or other media.
Multimodal
Combines text, vision, and audio in one model.

Context Window

Context window not disclosed.

Availability

API
Not available
Product / App
Not available
Open Source
Released
Enterprise

Pricing Model

Free / self-host
Open weights — pay only for compute.
Self-host

What it feels like

  • Language model from Microsoft — see the linked sources below for benchmark and review coverage

Best use cases

  • General-purpose tasks within Microsoft's deployment footprint
  • See the model spec and sources block for benchmarked use cases

Tools to try

Not ideal for

  • Tasks far outside the modalities listed in this model's spec
  • Workflows where a more recent successor in the same family scores higher

Microsoft Research AI4Science