mlsanityData to 14 Oct 2026

RouterArena: An Open Platform for Comprehensive Comparison of LLM Routers

arXiv 2510.00202 ↗First posted 30 Sep 2025cs.LGcited by 22

Not on the map. Why?

Abstract (arXiv)

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 makes choosing the right one increasingly challenging. 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 leaderboard updates. Leveraging our framework, we have produced the initial leaderboard with detailed metrics comparison as shown in Figure 1. Our framework for evaluating new routers is on https://github.com/RouteWorks/RouterArena. Our leaderboard is on https://routeworks.github.io/.

Key facts. Cited by 22 papers in the map (data through 14 Oct 2026). Builds on 22 of its 41 references that are in the map. First posted on arXiv 30 Sep 2025.

Builds on

22 of 41 references.

References · 22

  1. 2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,944
  2. 2024Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preferencecited by 1,184
  3. 2023FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performancecited by 853
  4. 2024RouteLLM: Learning to Route LLMs with Preference Datacited by 682
  5. 2019Is BERT Really Robust? A Strong Baseline for Natural Language Attack on Text Classification and Entailmentcited by 671
  6. 2024RouterBench: A Benchmark for Multi-LLM Routing Systemcited by 238
  7. 2024GraphRouter: A Graph-based Router for LLM Selectionscited by 165
  8. 2024RouterDC: Query-Based Router by Dual Contrastive Learning for Assembling Large Language Modelscited by 88
  9. 2025Universal Model Routing for Efficient LLM Inferencecited by 86
  10. 2025Router-R1: Teaching LLMs Multi-Round Routing and Aggregation via Reinforcement Learningcited by 72
  11. 2024Learning to Route LLMs with Confidence Tokenscited by 67
  12. 2025BEST-Route: Adaptive LLM Routing with Test-Time Optimal Computecited by 67
10 more
  1. 2025RouterEval: A Comprehensive Benchmark for Routing LLMs to Explore Model-level Scaling Up in LLMscited by 61
  2. 2025MixLLM: Dynamic Routing in Mixed Large Language Modelscited by 59
  3. 2024EmbedLLM: Learning Compact Representations of Large Language Modelscited by 48
  4. 2025IRT-Router: Effective and Interpretable Multi-LLM Routing via Item Response Theorycited by 40
  5. 2023Model Spider: Learning to Rank Pre-Trained Models Efficientlycited by 32
  6. 2023Tryage: Real-time, intelligent Routing of User Prompts to Large Language Modelscited by 30
  7. 2025Capability Instruction Tuning: A New Paradigm for Dynamic LLM Routingcited by 25
  8. 2024OptLLM: Optimal Assignment of Queries to Large Language Modelscited by 16
  9. 2025How Robust Are Router-LLMs? Analysis of the Fragility of LLM Routing Capabilitiescited by 11
  10. 2024Model-GLUE: Democratized LLM Scaling for A Large Model Zoo in the Wildcited by 9

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 21.

22 papers.

Sort:

By area:

  1. 2026LLMRouterBench: A Massive Benchmark and Unified Framework for LLM Routingcited by 38
  2. 2026Dynamic Model Routing and Cascading for Efficient LLM Inference: A Surveycited by 19
  3. 2026R2-Router: A New Paradigm for LLM Routing with Reasoningcited by 14
  4. 2026MMR-Bench: A Comprehensive Benchmark for Multimodal LLM Routingcited by 13
  5. 2026SWE-Router: Routing in Multi-turn Agentic Software Engineering Taskscited by 11
  6. 2025VL-RouterBench: A Benchmark for Vision-Language Model Routingcited by 8
  7. 2026The Replay Gap: Static Evaluation of Model Switching in LLM Agents Scores the Wrong Worldcited by 8
  8. 2026TwinRouterBench: Fast Static and Live Dynamic Evaluation for Realistic Agentic LLM Routingcited by 6
  9. 2026Route to Rome Attack: Directing LLM Routers to Expensive Models via Adversarial Suffix Optimizationcited by 5
  10. 2026Unsolvability Ceiling in Multi-LLM Routing: An Empirical Study of Evaluation Artifactscited by 4
  11. 2026Robust Batch-Level Query Routing for Large Language Models under Cost and Capacity Constraintscited by 3
  12. 2026Switchcraft: AI Model Router for Agentic Tool Callingcited by 3
10 more
  1. 2026SeqRoute: Global Budget-Aware Sequential LLM Routing via Offline Reinforcement Learningcited by 2
  2. 2026The Routing Plateau: Understanding the Accuracy Limits of LLM Routerscited by 1
  3. 2026DIRECT: When and Where Should You Allocate Test-Time Compute in Embodied Planners?cited by 1
  4. 2026KVShareArena: KV-Cache Reuse Across Contexts and Model Checkpointscited by 1
  5. 2026Dynamic LLM Routers are Often Misguidedcited by 1
  6. 2026OrcaRouter: A Production-Oriented LLM Router with Hybrid Offline-Online Learningcited by 0
  7. 2026SCOPE-Router: Cost-Aware Open-Set VLM Routing for Execution-Oriented Taskscited by 0
  8. 2026Routing Without Embeddings: Fast And Interpretable Routing With Regular Expressionscited by 0
  9. 2026Empowering Edge Agents: A Systematic Analysis of Edge-Cloud Collaboration in LLM Agent Executioncited by 0
  10. 2026Rethinking Quality in Large Language Model Routing: Security-Conditioned Model-and-Budget Selectioncited by 0