# CoEval: Ranking Language Models for Custom Tasks Without Labeled Data or Trustworthy Benchmarks

arXiv: https://arxiv.org/abs/2606.03650 · HTML: https://mlsanity.com/paper/2606.03650/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 35 references that are in the map.
- First posted on arXiv 2 Jun 2026.

## Builds on (most cited first, 30 of 31)

- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment](https://mlsanity.com/paper/2303.16634/) (2023)
- [LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code](https://mlsanity.com/paper/2403.07974/) (2024)
- [A Survey on LLM-as-a-Judge](https://mlsanity.com/paper/2411.15594/) (2024)
- [Length-Controlled AlpacaEval: A Simple Way to Debias Automatic Evaluators](https://mlsanity.com/paper/2404.04475/) (2024)
- [ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate](https://mlsanity.com/paper/2308.07201/) (2023)
- [From Generation to Judgment: Opportunities and Challenges of LLM-as-a-judge](https://mlsanity.com/paper/2411.16594/) (2024)
- [Dynabench: Rethinking Benchmarking in NLP](https://mlsanity.com/paper/2104.14337/) (2021)
- [Prometheus 2: An Open Source Language Model Specialized in Evaluating Other Language Models](https://mlsanity.com/paper/2405.01535/) (2024)
- [Justice or Prejudice? Quantifying Biases in LLM-as-a-Judge](https://mlsanity.com/paper/2410.02736/) (2024)
- [Replacing Judges with Juries: Evaluating LLM Generations with a Panel of Diverse Models](https://mlsanity.com/paper/2404.18796/) (2024)
- [JudgeBench: A Benchmark for Evaluating LLM-based Judges](https://mlsanity.com/paper/2410.12784/) (2024)
- [LiveBench: A Challenging, Contamination-Limited LLM Benchmark](https://mlsanity.com/paper/2406.19314/) (2024)
- [Self-Preference Bias in LLM-as-a-Judge](https://mlsanity.com/paper/2410.21819/) (2024)
- [A Careful Examination of Large Language Model Performance on Grade School Arithmetic](https://mlsanity.com/paper/2405.00332/) (2024)
- [Benchmark Data Contamination of Large Language Models: A Survey](https://mlsanity.com/paper/2406.04244/) (2024)
- [Preference Leakage: A Contamination Problem in LLM-as-a-judge](https://mlsanity.com/paper/2502.01534/) (2025)
- [The BiGGen Bench: A Principled Benchmark for Fine-grained Evaluation of Language Models with Language Models](https://mlsanity.com/paper/2406.05761/) (2024)
- [Foundational Autoraters: Taming Large Language Models for Better Automatic Evaluation](https://mlsanity.com/paper/2407.10817/) (2024)
- [AutoBencher: Towards Declarative Benchmark Construction](https://mlsanity.com/paper/2407.08351/) (2024)
- [Recent Advances in Large Langauge Model Benchmarks against Data Contamination: From Static to Dynamic Evaluation](https://mlsanity.com/paper/2502.17521/) (2025)
- [Do LLM Evaluators Prefer Themselves for a Reason?](https://mlsanity.com/paper/2504.03846/) (2025)
- [Play Favorites: A Statistical Method to Measure Self-Bias in LLM-as-a-Judge](https://mlsanity.com/paper/2508.06709/) (2025)
- [Constructing Domain-Specific Evaluation Sets for LLM-as-a-judge](https://mlsanity.com/paper/2408.08808/) (2024)
- [YourBench: Easy Custom Evaluation Sets for Everyone](https://mlsanity.com/paper/2504.01833/) (2025)
- [Leveraging LLMs as Meta-Judges: A Multi-Agent Framework for Evaluating LLM Judgments](https://mlsanity.com/paper/2504.17087/) (2025)
- [Generating Diverse Q&A Benchmarks for RAG Evaluation with DataMorgana](https://mlsanity.com/paper/2501.12789/) (2025)
- [CARE: Confounder-Aware Aggregation for Reliable LLM Evaluation](https://mlsanity.com/paper/2603.00039/) (2026)
- [How to Get Your LLM to Generate Challenging Problems for Evaluation](https://mlsanity.com/paper/2502.14678/) (2025)
- [A Judge-Aware Ranking Framework for Evaluating Large Language Models without Ground Truth](https://mlsanity.com/paper/2601.21817/) (2026)

## Built on by (most cited first, 2 of 2)

- [Clinical Communication Processing with Models Trained on LLM-Generated Synthetic Data: A Structured Survey and Novel Application Case Studies](https://mlsanity.com/paper/2608.05993/) (2026)
- [Clinical Intent Extraction: A FHIR-Aligned Representation and the CIRCA Benchmark](https://mlsanity.com/paper/2609.29479/) (2026)

## Abstract (arXiv)

Selecting a pretrained language model, or evaluating a fine-tuned one, for a specific application is a high-value decision, yet the public benchmarks used to make it are poorly suited: a generic benchmark need not reflect a particular sub-domain or sub-task, and its scores are suspect when its items have leaked into pretraining and are recalled rather than solved. We present CoEval, an open framework that supplies a trustworthy, task-specific signal through ensemble self-evaluation: from a task or domain description, a pool of models rotates through all three roles, teacher, student, and judge, to generate a fresh, contamination-free benchmark, answer it, and score one another, with no human labels or raters. Because every model also answers as a student, the responses are the data that weight each question by its discriminative power and each judge by its consensus with the panel. Where ground truth exists, CoEval recovers the true ranking and tracks objective correctness at rho=0.86, and the weighting recovers the gold ranking of thirteen models at Spearman 0.95. Reliability comes from panel composition, not size: this label-free weighting zeroes out broken judges and down-weights saturated questions, so neither distorts the ranking. Generated items show zero verbatim overlap with five public benchmarks, the panel cancels verbosity bias and precludes same-family self-preference, and rankings are domain-specific: three different models top four de-novo domains, so a generic leaderboard misdirects most practitioners. The same pipeline reruns on each model release, giving any team a contamination-free leaderboard for its application.