# CodeJudgeBench: Benchmarking LLM-as-a-Judge for Coding Tasks

arXiv: https://arxiv.org/abs/2507.10535 · HTML: https://mlsanity.com/paper/2507.10535/

## Key facts

- Cited by 33 papers in the map (data through 14 Oct 2026).
- Builds on 60 of its 78 references that are in the map.
- First posted on arXiv 14 Jul 2025.

## Builds on (most cited first, 30 of 60)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [Program Synthesis with Large Language Models](https://mlsanity.com/paper/2108.07732/) (2021)
- [Emergent Abilities of Large Language Models](https://mlsanity.com/paper/2206.07682/) (2022)
- [LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code](https://mlsanity.com/paper/2403.07974/) (2024)
- [Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters](https://mlsanity.com/paper/2408.03314/) (2024)
- [Competition-Level Code Generation with AlphaCode](https://mlsanity.com/paper/2203.07814/) (2022)
- [A Survey on LLM-as-a-Judge](https://mlsanity.com/paper/2411.15594/) (2024)
- [Teaching Large Language Models to Self-Debug](https://mlsanity.com/paper/2304.05128/) (2023)
- [BloombergGPT: A Large Language Model for Finance](https://mlsanity.com/paper/2303.17564/) (2023)
- [Phi-4 Technical Report](https://mlsanity.com/paper/2412.08905/) (2024)
- [CodeBLEU: a Method for Automatic Evaluation of Code Synthesis](https://mlsanity.com/paper/2009.10297/) (2020)
- [Prometheus 2: An Open Source Language Model Specialized in Evaluating Other Language Models](https://mlsanity.com/paper/2405.01535/) (2024)
- [CodeT: Code Generation with Generated Tests](https://mlsanity.com/paper/2207.10397/) (2022)
- [JudgeLM: Fine-tuned Large Language Models are Scalable Judges](https://mlsanity.com/paper/2310.17631/) (2023)
- [Demystifying Long Chain-of-Thought Reasoning in LLMs](https://mlsanity.com/paper/2502.03373/) (2025)
- [Humans or LLMs as the Judge? A Study on Judgement Biases](https://mlsanity.com/paper/2402.10669/) (2024)
- [JudgeBench: A Benchmark for Evaluating LLM-based Judges](https://mlsanity.com/paper/2410.12784/) (2024)
- [PandaLM: An Automatic Evaluation Benchmark for LLM Instruction Tuning Optimization](https://mlsanity.com/paper/2306.05087/) (2023)
- [FinGPT: Open-Source Financial Large Language Models](https://mlsanity.com/paper/2306.06031/) (2023)
- [RM-Bench: Benchmarking Reward Models of Language Models with Subtlety and Style](https://mlsanity.com/paper/2410.16184/) (2024)
- [Generative Judge for Evaluating Alignment](https://mlsanity.com/paper/2310.05470/) (2023)
- [RM-R1: Reward Modeling as Reasoning](https://mlsanity.com/paper/2505.02387/) (2025)

## Built on by (most cited first, 30 of 33)

- [Automatic Failure Attribution and Critical Step Prediction Method for Multi-Agent Systems Based on Causal Inference](https://mlsanity.com/paper/2509.08682/) (2025)
- [Incentivizing Agentic Reasoning in LLM Judges via Tool-Integrated Reinforcement Learning](https://mlsanity.com/paper/2510.23038/) (2025)
- [From Code Foundation Models to Agents and Applications: A Comprehensive Survey and Practical Guide to Code Intelligence](https://mlsanity.com/paper/2511.18538/) (2025)
- [DevBench: A Realistic, Developer-Informed Benchmark for Code Generation Models](https://mlsanity.com/paper/2601.11895/) (2026)
- [SciML Agents: Write the Solver, Not the Solution](https://mlsanity.com/paper/2509.09936/) (2025)
- [Secure Code Generation via Online Reinforcement Learning with Vulnerability Reward Model](https://mlsanity.com/paper/2602.07422/) (2026)
- [Foundational Automatic Evaluators: Scaling Multi-Task Generative Evaluator Training for Reasoning-Centric Domains](https://mlsanity.com/paper/2510.17793/) (2025)
- [SWE-Cycle: Benchmarking Code Agents across the Complete Issue Resolution Cycle](https://mlsanity.com/paper/2605.13139/) (2026)
- [Scaling Large Reasoning Models beyond Human Supervision: A Path toward Superintelligence](https://mlsanity.com/paper/2608.31075/) (2026)
- [Gistify! Codebase-Level Understanding via Runtime Execution](https://mlsanity.com/paper/2510.26790/) (2025)
- [Bias in the Loop: Auditing LLM-as-a-Judge for Software Engineering](https://mlsanity.com/paper/2604.16790/) (2026)
- [Self Improvement via Fast Tree-search](https://mlsanity.com/paper/2609.19526/) (2026)
- [PDE-SHARP: PDE Solver Hybrids through Analysis and Refinement Passes](https://mlsanity.com/paper/2511.00183/) (2025)
- [CodeCircuit: Toward Inferring LLM-Generated Code Correctness via Attribution Graphs](https://mlsanity.com/paper/2602.07080/) (2026)
- [SLMJury: Can Small Language Models Judge as Well as Large Ones?](https://mlsanity.com/paper/2606.07810/) (2026)
- [ProactiveBench: Benchmarking Proactiveness in Multimodal Large Language Models](https://mlsanity.com/paper/2603.19466/) (2026)
- [Benchmarking Code LLM-as-a-Judge via Constrained Perturbation and Calibration](https://mlsanity.com/paper/2512.20159/) (2025)
- [Simple Role Assignment is Extraordinarily Effective for Safety Alignment](https://mlsanity.com/paper/2602.00061/) (2026)
- [Comparing Developer and LLM Biases in Code Evaluation](https://mlsanity.com/paper/2603.24586/) (2026)
- [How Trustworthy Are LLM-as-Judge Ratings for Interpretive Responses? Implications for Qualitative Research Workflows](https://mlsanity.com/paper/2604.00008/) (2026)
- [Themis: Training Robust Multilingual Code Reward Models for Flexible Multi-Criteria Scoring](https://mlsanity.com/paper/2605.00754/) (2026)
- [ReMedi: Reasoner for Medical Clinical Prediction](https://mlsanity.com/paper/2605.01474/) (2026)
- [AI-Driven Decision-Making System for Hiring Process](https://mlsanity.com/paper/2512.20652/) (2025)
- [Making Bias Non-Predictive: Training Robust LLM Reasoning via Reinforcement Learning](https://mlsanity.com/paper/2602.01528/) (2026)
- [From Feelings to Metrics: Understanding and Formalizing How Users Vibe-Test LLMs](https://mlsanity.com/paper/2604.14137/) (2026)
- [OpsLLM: Construction of Large Language Model for Software Operations with Multi-stage Learning](https://mlsanity.com/paper/2605.02906/) (2026)
- [PYTHALAB-MERA: Validation-Grounded Memory, Retrieval, and Acceptance Control for Frozen-LLM Coding Agents](https://mlsanity.com/paper/2605.08468/) (2026)
- [CriterAlign: Criterion-Centric Rationale Alignment for Code Preference Judging](https://mlsanity.com/paper/2605.19665/) (2026)
- [AutoSG: LLM-Driven Solver Generation Solely from Task Prompts for Expensive Optimization](https://mlsanity.com/paper/2605.25658/) (2026)
- [SynCity 3000: Bootstrapping Scene-Scale 3D Diffusion](https://mlsanity.com/paper/2607.05392/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) have significantly advanced the state-of-the-art in various coding tasks. Beyond directly answering user queries, LLMs can also serve as judges, assessing and comparing the quality of responses generated by other models. Such an evaluation capability is crucial both for benchmarking different LLMs and for improving response quality through response ranking. However, despite the growing adoption of the LLM-as-a-Judge paradigm, its effectiveness in coding scenarios remains underexplored due to the absence of dedicated benchmarks. To address this gap, we introduce CodeJudgeBench, a benchmark explicitly designed to evaluate the performance of LLM-as-a-Judge models across three critical coding tasks: code generation, code repair, and unit test generation. Through comprehensive benchmarking of 26 LLM-as-a-Judge models, we find that recent thinking models significantly outperform non-thinking models on our carefully designed code judging tasks. Notably, even relatively small thinking models, such as Qwen3-8B, can outperform specially trained LLM-as-a-Judge models up to 70B in size. Nevertheless, all models still exhibit significant randomness in their judgment of coding tasks. For pairwise judging tasks, simply changing the order in which responses are presented can substantially impact accuracy. In addition, when judging code and unit tests written by different LLMs, LLM-as-a-Judge models also show variance in performance. This sensitivity raises concerns about the reliability and consistency of LLM-as-a-Judge in coding scenarios. Lastly, we study optimal prompting strategies for LLM-as-a-Judge. We find that using pair-wise comparison outperforms scalar point-wise judging. Furthermore, retaining comments and reasoning in the full, unprocessed LLM response leads to improved judge performance.