Find the best LLM for your task

Choose your engineering discipline, the kinds of task you need the model for and the hardware you will run it on. The Benchmarking Assistant ranks the open language models that fit your machine and your work, using published benchmark data.

Task profile

Discipline

Task types

Physics reasoning Mathematical problem solving Code generation Technical documentation Simulation interpretation Standards compliance

Hardware profile

GPU model

VRAM (GB)

System RAM (GB)

Accept quantised models

Deployment

Checking how many models fit your hardware…

Run type

Published data Free
Rank instantly using cached published benchmark results. Live run Subscribers
A subscription is required for live runs on your own hardware estimate.