Field Notes
A collection of research, projects, and teams we’ve learned from and been inspired by.
- FN-01 · RTL · datapathHWE Bench: RISC-V CPU design benchmark for LLMs (opens in a new tab)
- FN-02 · Mesh · stressEMVal: an electromagnetics dataset from Arena Physica (opens in a new tab)
- FN-03 · Verilog to logicVerilogEval: Evaluating Large Language Models for Verilog Code Generation (opens in a new tab)
- FN-04 · RTL · datapathRTLLM: An Open-Source Benchmark for Design RTL Generation with Large Language Model (opens in a new tab)
- FN-05 · Drawing · Q&ADesignQA: A Multimodal Benchmark for Evaluating Large Language Models' Understanding of Engineering Documentation (opens in a new tab)
- FN-06 · Mesh · stressFEABench: Evaluating Language Models on Multiphysics Reasoning Ability (opens in a new tab)
- FN-07 · Harness · pass/failVerilogEval, the benchmark's code (opens in a new tab)
- FN-08 · Pages to Q&A pairsDesignQA, the benchmark's code and data (opens in a new tab)