# MLIP Arena

## Docs

- [MLIP and MLIPEnum](https://mintlify.wiki/atomind-ai/mlip-arena/api/models/mlip.md): API reference for the MLIP base class, MLIPEnum, and MLIPMap.
- [MLIPCalculator](https://mintlify.wiki/atomind-ai/mlip-arena/api/models/mlip-calculator.md): API reference for the MLIPCalculator class — the ASE-compatible calculator wrapper for MLIP models.
- [Model Registry](https://mintlify.wiki/atomind-ai/mlip-arena/api/models/registry.md): Reference for the MLIP Arena model registry — the registry.yaml file, all fields, and the complete model table.
- [ELASTICITY — Elastic Tensor](https://mintlify.wiki/atomind-ai/mlip-arena/api/tasks/elasticity.md): Compute the full elastic tensor, bulk modulus, and related mechanical properties using finite strain deformations.
- [EOS — Equation of State](https://mintlify.wiki/atomind-ai/mlip-arena/api/tasks/eos.md): Compute the Birch–Murnaghan equation of state, bulk modulus, and equilibrium volume for a structure.
- [MD — Molecular Dynamics](https://mintlify.wiki/atomind-ai/mlip-arena/api/tasks/md.md): Run NVE, NVT, or NPT molecular dynamics simulations using ASE integrators with optional temperature and pressure schedules.
- [NEB — Nudged Elastic Band](https://mintlify.wiki/atomind-ai/mlip-arena/api/tasks/neb.md): Compute minimum energy paths and energy barriers using the nudged elastic band method with ASE.
- [OPT — Structure Optimization](https://mintlify.wiki/atomind-ai/mlip-arena/api/tasks/opt.md): Run geometry optimization on an atomic structure using ASE optimizers and filters.
- [PHONON — Phonon Calculation](https://mintlify.wiki/atomind-ai/mlip-arena/api/tasks/phonon.md): Compute phonon dispersion, density of states, and thermal properties using Phonopy and an MLIP calculator.
- [Calculator utilities](https://mintlify.wiki/atomind-ai/mlip-arena/api/utils/calculator.md): Functions for constructing ASE calculators from MLIP models, with optional dispersion correction.
- [Device utilities](https://mintlify.wiki/atomind-ai/mlip-arena/api/utils/device.md): Functions for selecting the optimal compute device (GPU, MPS, or CPU) for MLIP calculations.
- [Combustion](https://mintlify.wiki/atomind-ai/mlip-arena/benchmarks/combustion.md): Testing MLIP reactive chemistry capability through hydrogen combustion molecular dynamics, measuring yield, reaction enthalpy, and simulation stability.
- [Energy-volume scans](https://mintlify.wiki/atomind-ai/mlip-arena/benchmarks/energy-volume-scans.md): Evaluating energy–volume profiles across WBM dataset structures without structure relaxation, using uniaxial strain.
- [Equation of state](https://mintlify.wiki/atomind-ai/mlip-arena/benchmarks/equation-of-state.md): Evaluating bulk moduli and energy–volume curves for WBM bulk crystals using Birch-Murnaghan fitting.
- [Homonuclear diatomics](https://mintlify.wiki/atomind-ai/mlip-arena/benchmarks/homonuclear-diatomics.md): Evaluating MLIP dissociation energy curves for elemental homonuclear pairs — the most fundamental test of interatomic interactions.
- [Benchmarks overview](https://mintlify.wiki/atomind-ai/mlip-arena/benchmarks/overview.md): How MLIP Arena evaluates foundation models beyond DFT error metrics, across Fundamentals and Molecular Dynamics categories.
- [MD stability](https://mintlify.wiki/atomind-ai/mlip-arena/benchmarks/stability.md): Testing MLIP survival rate and inference speed under NVT heating and NPT compression ramps on RM24 crystal structures.
- [System architecture](https://mintlify.wiki/atomind-ai/mlip-arena/concepts/architecture.md): How MLIP Arena orchestrates models, tasks, flows, and benchmarks into a unified evaluation platform.
- [Models](https://mintlify.wiki/atomind-ai/mlip-arena/concepts/models.md): How MLIP Arena registers, loads, and exposes foundation MLIP models through a unified ASE Calculator interface.
- [Tasks](https://mintlify.wiki/atomind-ai/mlip-arena/concepts/tasks.md): Composable, Prefect-decorated operations that run one physical simulation on one structure.
- [Workflows & Prefect](https://mintlify.wiki/atomind-ai/mlip-arena/concepts/workflows.md): How Prefect flows enable parallel benchmark execution, caching, and HPC-scale orchestration in MLIP Arena.
- [Adding a new benchmark](https://mintlify.wiki/atomind-ai/mlip-arena/contributing/add-benchmark.md): Design and register a new benchmark task that tests a physical property or failure mode.
- [Adding a new model](https://mintlify.wiki/atomind-ai/mlip-arena/contributing/add-model.md): Register a pretrained MLIP in MLIP Arena so it participates in all benchmarks.
- [Contributing to MLIP Arena](https://mintlify.wiki/atomind-ai/mlip-arena/contributing/overview.md): How to contribute new models, benchmarks, and improvements to MLIP Arena.
- [Installation](https://mintlify.wiki/atomind-ai/mlip-arena/installation.md): Install MLIP Arena via PyPI or from source with all pretrained models.
- [MLIP Arena](https://mintlify.wiki/atomind-ai/mlip-arena/introduction.md): Fair and transparent benchmark of machine learning interatomic potentials (MLIPs), beyond basic error metrics
- [Quickstart](https://mintlify.wiki/atomind-ai/mlip-arena/quickstart.md): Run your first MLIP Arena benchmark in minutes.
- [Elasticity](https://mintlify.wiki/atomind-ai/mlip-arena/tasks/elasticity.md): Compute the full elastic tensor and derived moduli from finite-strain stress calculations.
- [Equation of state](https://mintlify.wiki/atomind-ai/mlip-arena/tasks/equation-of-state.md): Compute the energy-volume curve and fit a Birch-Murnaghan EOS to extract bulk modulus and equilibrium volume.
- [Molecular dynamics](https://mintlify.wiki/atomind-ai/mlip-arena/tasks/molecular-dynamics.md): Run NVE, NVT, or NPT molecular dynamics simulations with flexible temperature and pressure scheduling.
- [Nudged elastic band](https://mintlify.wiki/atomind-ai/mlip-arena/tasks/neb.md): Find minimum-energy transition paths and energy barriers between two structures using the nudged elastic band (NEB) method.
- [Tasks overview](https://mintlify.wiki/atomind-ai/mlip-arena/tasks/overview.md): Modular, Prefect-powered computational tasks for benchmarking MLIPs.
- [Phonons](https://mintlify.wiki/atomind-ai/mlip-arena/tasks/phonon.md): Calculate phonon band structures, density of states, and thermal properties using phonopy.
- [Structure optimization](https://mintlify.wiki/atomind-ai/mlip-arena/tasks/structure-optimization.md): Relax atomic positions and cell parameters to a local energy minimum using ASE optimizers.