RouterEval

Emerging

1papers using it

2025first seen

RouterEval is a benchmark designed for router research in large language models (LLMs), containing over 200 million performance records from 12 popular LLM evaluations across various areas, based on more than 8,500 different LLMs.

🔎 Find this dataset

Papers using RouterEval (1)

RouterEval: A Comprehensive Benchmark for Routing LLMs to Explore Model-level Scaling Up in LLMs2025