SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2410.12784 · ICLR · 2025

JudgeBench: A Benchmark for Evaluating LLM-based Judges

Ion Stoica, Siyuan Zhuang, Kyle Montgomery, Chenguang Wang, Sijun Tan, William Tang, Alejandro Cuadron, Raluca Popa

arXiv · PDF · Open in the Atlas

Code that ran

3 of 4 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 1 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 2 failures of our instrument; 1 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2410.12784.json · badge: /api/ran/2410.12784.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
ScalerLab/JudgeBench canonical (classifier label)
classifier basis: census
3 ran · 1 no recorded run
FunctionStatusWhere it lives
compute_final_metrics Ran
ran, honoured the contract we drafted
ScalerLab/JudgeBench/utils/metrics.py
pointer only (licence: NONE) · get_code("2bb16d114379b0a9")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ScalerLab/JudgeBench when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

flip_judgment Ran
ran; our contract draft was wrong, not the code
ScalerLab/JudgeBench/utils/metrics.py
pointer only (licence: NONE) · get_code("e713d200f87c80bc")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ScalerLab/JudgeBench when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

read_jsonl Ran
ran; our contract draft was wrong, not the code
ScalerLab/JudgeBench/utils/file_operations.py
pointer only (licence: NONE) · get_code("195bbcd43396ba20")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ScalerLab/JudgeBench when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

render_template Not yet run
unverified (harvested, no recorded run)
ScalerLab/JudgeBench/utils/prompts.py
pointer only (licence: NONE) · get_code("1f8fad089086e873")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ScalerLab/JudgeBench when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 4 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

LLM-based judges have emerged as a scalable alternative to human evaluation and are increasingly used to assess, compare, and improve models. However, the reliability of LLM-based judges themselves is rarely scrutinized. As LLMs become more advanced, their responses grow more sophisticated, requiring stronger judges to evaluate them. Existing benchmarks primarily focus on a judge's alignment with human preferences, but often fail to account for more challenging tasks where crowdsourced human preference is a poor indicator of factual and logical correctness. To address this, we propose a novel evaluation framework to objectively evaluate LLM-based judges. Based on this framework, we propose JudgeBench, a benchmark for evaluating LLM-based judges on challenging response pairs spanning knowledge, reasoning, math, and coding. JudgeBench leverages a novel pipeline for converting existing difficult datasets into challenging response pairs with preference labels reflecting objective correctness. Our comprehensive evaluation on a collection of prompted judges, fine-tuned judges, multi-agent judges, and reward models shows that JudgeBench poses a significantly greater challenge than previous benchmarks, with many strong models (e.g., GPT-4o) performing just slightly better than random guessing. Overall, JudgeBench offers a reliable platform for assessing increasingly advanced LLM-based judges. Data and code are available at https://github.com/ ScalerLab/JudgeBench.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2410.12784")
get_code_for_paper("2410.12784")
have("2410.12784")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2410.12784.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2410.12784.svg)](https://syntology.ai/paper/2410.12784)

Connect an agent — have() is free.