Papers › RouterBench: A Benchmark for Multi-LLM Routing System

RouterBench: A Benchmark for Multi-LLM Routing System

18 Mar 2024arXiv:2403.12031archive 2025-07-28

Qitian Jason Hu, Jacob Bieker, Xiuyu Li, Nan Jiang, Benjamin Keigwin, Gaurav Ranganath, Kurt Keutzer, Shriyash Kaustubh Upadhyay

As the range of applications for Large Language Models (LLMs) continues to grow, the demand for effective serving solutions becomes increasingly critical. Despite the versatility of LLMs, no single model can optimally address all tasks and applications, particularly when balancing performance with cost. This limitation has led to the development of LLM routing systems, which combine the strengths of various models to overcome the constraints of individual LLMs. Yet, the absence of a standardized benchmark for evaluating the performance of LLM routers hinders progress in this area. To bridge this gap, we present RouterBench, a novel evaluation framework designed to systematically assess the efficacy of LLM routing systems, along with a comprehensive dataset comprising over 405k inference outcomes from representative LLMs to support the development of routing strategies. We further propose a theoretical framework for LLM routing, and deliver a comparative analysis of various routing approaches through RouterBench, highlighting their potentials and limitations within our evaluation framework. This work not only formalizes and advances the development of LLM routing systems but also sets a standard for their assessment, paving the way for more accessible and economically viable LLM deployments. The code and data are available at https://github.com/withmartian/routerbench.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 13 code samples harvested from 1 repository linked to this paper: 9 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 9 where Syntology's instrument failed) · 4 unverified. Where Syntology's instrument failed: 7 where our contract draft was wrong; 2 where the contract check could not run; failures of Syntology's instrument, not of the code. Every run on this page is a failure of Syntology's instrument, not of the code.

By repository: official repository: 13 samples from 1 repository, 9 ran (0 with no instrument failure; 9 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

No sample is linked to this paper from 1 of its repositories that Syntology harvested for other papers:

Levels written on 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

withmartian/routerbench officialmentioned in papermentioned on GitHubMITSyntology: 13 samples, 9 ran (9 instrument-failed) · 4 unverified report
codelion/adaptive-classifier pytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Overcoming catastrophic forgetting in neural networks (arXiv:1612.00796; that paper's own run record: 16 ran (of which 8 constructed an object rather than computing a result; 12 with no instrument failure: 2 honoured, 0 violated, 10 with no contract checked; 4 where Syntology's instrument failed) · 6 unverified) and Transformer-Squared: Self-adaptive LLMs (arXiv:2501.06252; that paper's own run record: 6 ran (of which 1 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified); nothing checks that they implement this paper's method. report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

13 samples harvested: 9 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 9 where Syntology's instrument failed) · 4 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Every run on this page is a failure of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

7ran · our draft was wrong
2ran; the contract check could not run
4unverified

Licence: 0 of the 13 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from withmartian/routerbench. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

withmartian/routerbench official repository 13 samples, 9 ran (9 instrument-failed) · 4 unverified
convert_to_wide_format convertors/common.py ran · our draft was wrong MIT (permissive) · b35a977d197d148b · report fixture: signature dataset_df:DataFrame/0/?, with_cost_col:bool/0/bool · returned DataFrame · level recorded 2026-09-24
extract_prompt_and_response convertors/martian_evals_convertor.py ran · our draft was wrong MIT (permissive) · 896695dc98b3fd4b · report fixture: signature x:list/1/dict · returned list · level recorded 2026-09-24
generate_datetime_str utils.py ran · our draft was wrong MIT (permissive) · b813cf6af3749d3b · report fixture: signature hour:bool/0/bool, minute:bool/0/bool · returned str · level recorded 2026-09-24
get_highest_accuracy_lowest_cost convertors/common.py ran; the contract check could not run (RAISES) MIT (permissive) · 00e7700fc4378a52 · report fixture: signature row:Series/1/float, models_to_route:list/1/str · returned str · level recorded 2026-09-24
get_models_to_route utils.py ran · our draft was wrong MIT (permissive) · 0d896d266dd0a8ac · report fixture: signature dataset_df:DataFrame/0/? · returned list · level recorded 2026-09-24
get_non_descreasing_convex_hull_of evaluation/AIQ.py ran; the contract check could not run (RAISES) MIT (permissive) · b37ae418bd1de8e1 · report fixture: signature points:ndarray/2/float · returned ndarray · level recorded 2026-09-24
parse_model_parameters utils.py ran · our draft was wrong MIT (permissive) · 6b8f114f358fc83e · report fixture: signature model_string:str/0/str · returned dict · level recorded 2026-09-24
parse_params_from_model_name evaluate_utils.py ran · our draft was wrong fingerprinted MIT (permissive) · 40d13812d7dd1e9b · report fixture: signature model_name:str/0/str · returned dict · level recorded 2026-09-24
select_prompts convertors/martian_evals_convertor.py ran · our draft was wrong fingerprinted MIT (permissive) · acf2e9aa1fa7e76b · report fixture: signature x:str/0/str · returned list · level recorded 2026-09-24
calc_AIQ evaluation/AIQ.py unverified MIT (permissive) · 90cd93f85d0260b9 · report
calculate_area_under_curve evaluation/AIQ.py unverified MIT (permissive) · 7b3c8ab1435797c3 · report
save_cache_to_disk embedding/cache.py unverified MIT (permissive) · 9854f43d010dc0f8 · report
save_results in 8 papers evaluate_utils.py unverified MIT (permissive) · 8b7465494e9692ff · report

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections