Inference Optimization
TensorRT Edge-LLM achieves significant inference acceleration on Jetson AGX Thor edge platform, substantially improving AI agent deployment performance at the edge.
🆚 Compare See LICENSE file Edge AI TensorRT Jetson
ScientificML
A provenance-bearing benchmark for verifying symbolic candidate solutions to PDEs, containing 20 records with generator outputs, verification cases, and human annotations for assessing symbolic solver reliability.
🆚 Compare See LICENSE file PDE Symbolic Solving Benchmark
PDE Benchmark / Multi-Equation
Large-scale PDE benchmark covering heat, advection-diffusion and fluid dynamics - supports fair comparison of data-driven and physics-informed methods.
🆚 Compare MIT License Benchmark PDE CFD
3D Turbulence (DNS Validation)
2026 3D turbulent DNS benchmark with 5 tasks and controlled generalization splits, designed to test extrapolation of turbulence models.
🆚 Compare MIT License Turbulence DNS 3D
Geophysics / Inverse Problem
LANL's large-scale FWI benchmark - 12 datasets, 2.1 TB - reconstructing subsurface velocity from seismic data with data-driven methods, serving carbon storage, reservoir and earthquake applications.
🆚 Compare Data CC BY-NC-SA 4.0 (code BSD-3) Geophysics Inverse Problem Seismic
PDE Benchmark / Differentiable Solver
Microsoft Research's open-source PDE benchmark suite with differentiable solvers and spatiotemporal dynamics data for evaluating long-horizon rollout stability.
🆚 Compare MIT PDE Benchmark Differentiable Solver
Multiphysics / PDE - 16 Domains
Unified benchmark spanning 16 physical domains, dubbed the 'ImageNet moment of physical ML', with PyTorch API, pretrained baselines and HF streaming.
🆚 Compare Per subset (mostly CC-BY / code MIT) Multiphysics Benchmark PyTorch
Must-Read Benchmark Paper
Proposes a unified benchmark across 16 physical domains, arguing for cross-domain pretraining gains - a must-read for physics foundation models.
🆚 Compare Paper (see publication page) Benchmark Physics Foundation Model Survey
