ALUE: leaderboard
MITRE and FAA aerospace LLM framework (AIAA 2025): multiple-choice aviation knowledge exam questions, extractive QA on NTSB narratives, summarisation and RAG over FAA orders, each with its own metric.
Source: doi.org.
Interactive version: theaggregate.ai/benchmark?slug=alue · How It Works · Data refreshed daily, snapshot 2026-09-05.