RouterArena: An Open Platform for Comprehensive Comparison of LLM Routers
Yifan Lu, Rixin Liu, Jiayi Yuan, Xingqi Cui, Shenrun Zhang, Hongyi Liu, Jiarong Xing
Abstract
Today's LLM ecosystem comprises a wide spectrum of models that differ in size, capability, and cost. No single model is optimal for all scenarios; hence, LLM routers have become essential for selecting the most appropriate model under varying circumstances. However, the rapid emergence of various routers has led to fragmented evaluation practices and inconsistent metrics, making it difficult to systematically assess progress in this space. To address this problem, we need a comprehensive router comparison and a standardized leaderboard, similar to those available for models. In this work, we introduce RouterArena, the first open platform enabling comprehensive comparison of LLM routers. RouterArena has (1) a principally constructed dataset with broad knowledge domain coverage, (2) distinguishable difficulty levels for each domain, (3) an extensive list of evaluation metrics, and (4) an automated framework for evaluation and leaderboard updates. Leveraging this framework, we have produced the initial leaderboard with detailed metrics comparison. Figure1 provides a preview of the leaderboard. The complete framework and the latest router leaderboard are publicly available at https://routeworks.github.io/
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Cited by top-tier papers3
- R2-Router: A New Paradigm for LLM Routing with ReasoningJiaqi Xue, Qian Lou, Jiarong Xing, Heng HuangICML 2026 · 12 citations
- VL-RouterBench: A Benchmark for Vision–Language Model RoutingZhehao Huang, Baijiong Lin, Jingyuan Zhang, Jingying Wang et al.CVPR 2026 · 6 citations
- Route to Rome Attack: Directing LLM Routers to Expensive Models via Adversarial Suffix OptimizationHaochun Tang, Yuliang Yan, Jiahua Lu, Huaxiao Liu et al.ACL 2026 · 3 citations
Builds on12
- Is BERT Really Robust? A Strong Baseline for Natural Language Attack on Text Classification and EntailmentDi Jin, Zhijing Jin, Joey Tianyi Zhou, Peter SzolovitsAAAI 2020 · 1,333 citations
- Chatbot Arena: An Open Platform for Evaluating LLMs by Human PreferenceWei-Lin Chiang, Lianmin Zheng, Ying Sheng, Anastasios Nikolas Angelopoulos et al.ICML 2024 · 1,212 citations
- Efficient Memory Management for Large Language Model Serving with PagedAttentionWoosuk Kwon, Zhuohan Li, Siyuan Zhuang, Ying Sheng et al.SOSP 2023 · 1,016 citations
- RouterDC: Query-Based Router by Dual Contrastive Learning for Assembling Large Language ModelsShuhao Chen, Weisen Jiang, Baijiong Lin, James T. Kwok et al.NeurIPS 2024 · 113 citations
- Universal Model Routing for Efficient LLM InferenceWittawat Jitkrittum, Harikrishna Narasimhan, Ankit Singh Rawat, Jeevesh Juneja et al.ICLR 2026 · 99 citations
Related papers
- GraphArena: Evaluating and Exploring Large Language Models on Graph ComputationJianheng Tang, Qifan Zhang, Yuhan Li, Nuo Chen et al.ICLR 2025
- DiSRouter: Distributed Self-Routing for LLM SelectionsHang Zheng, Hongshen Xu, Yongkai.lin, Shuai Fan et al.ICLR 2026 · 6 citations
- Arena-lite: Efficient and Reliable Large Language Model Evaluation via Tournament-Based Direct ComparisonsSeonil Son, Ju-Min Oh, Heegon Jin, Cheolhun Jang et al.EMNLP 2025
- WorkArena: How Capable are Web Agents at Solving Common Knowledge Work Tasks?Alexandre Drouin, Maxime Gasse, Massimo Caccia, Issam H. Laradji et al.ICML 2024 · 188 citations
- Auto-Arena: Automating LLM Evaluations with Agent Peer Battles and Committee DiscussionsRuochen Zhao, Wenxuan Zhang, Yew Ken Chia, Weiwen Xu et al.ACL 2025 · 34 citations
