# Same Input, Different Scores: A Multi Model Study on the Inconsistency of LLM Judge

arXiv: https://arxiv.org/abs/2603.04417 · HTML: https://mlsanity.com/paper/2603.04417/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 24 of its 28 references that are in the map.
- First posted on arXiv 4 Feb 2026.

## Builds on (most cited first, 24 of 24)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [The Curious Case of Neural Text Degeneration](https://mlsanity.com/paper/1904.09751/) (2019)
- [Large Language Models are not Fair Evaluators](https://mlsanity.com/paper/2305.17926/) (2023)
- [Length-Controlled AlpacaEval: A Simple Way to Debias Automatic Evaluators](https://mlsanity.com/paper/2404.04475/) (2024)
- [From Generation to Judgment: Opportunities and Challenges of LLM-as-a-judge](https://mlsanity.com/paper/2411.16594/) (2024)
- [Is ChatGPT a Good NLG Evaluator? A Preliminary Study](https://mlsanity.com/paper/2303.04048/) (2023)
- [JudgeLM: Fine-tuned Large Language Models are Scalable Judges](https://mlsanity.com/paper/2310.17631/) (2023)
- [NLP Evaluation in trouble: On the Need to Measure LLM Data Contamination for each Benchmark](https://mlsanity.com/paper/2310.18018/) (2023)
- [SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal](https://mlsanity.com/paper/2406.14598/) (2024)
- [Benchmarking Cognitive Biases in Large Language Models as Evaluators](https://mlsanity.com/paper/2309.17012/) (2023)
- [Is LLM-as-a-Judge Robust? Investigating Universal Adversarial Attacks on Zero-shot LLM Assessment](https://mlsanity.com/paper/2402.14016/) (2024)
- [The Good, The Bad, and The Greedy: Evaluation of LLMs Should Not Ignore Non-Determinism](https://mlsanity.com/paper/2407.10457/) (2024)
- [An Empirical Study of LLM-as-a-Judge for LLM Evaluation: Fine-tuned Judge Model is not a General Substitute for GPT-4](https://mlsanity.com/paper/2403.02839/) (2024)
- [Non-Determinism of "Deterministic" LLM Settings](https://mlsanity.com/paper/2408.04667/) (2024)
- [Learning to Plan & Reason for Evaluation with Thinking-LLM-as-a-Judge](https://mlsanity.com/paper/2501.18099/) (2025)
- [LLM Comparative Assessment: Zero-shot NLG Evaluation through Pairwise Comparisons using Large Language Models](https://mlsanity.com/paper/2307.07889/) (2023)
- [Can You Trust LLM Judgments? Reliability of LLM-as-a-Judge](https://mlsanity.com/paper/2412.12509/) (2024)
- [Human-Centered Design Recommendations for LLM-as-a-Judge](https://mlsanity.com/paper/2407.03479/) (2024)
- [Improve LLM-as-a-Judge Ability as a General Ability](https://mlsanity.com/paper/2502.11689/) (2025)
- [Exploring Large Language Models for Feature Selection: A Data-centric Perspective](https://mlsanity.com/paper/2408.12025/) (2024)
- [Blueprint First, Model Second: A Framework for Deterministic LLM Workflow](https://mlsanity.com/paper/2508.02721/) (2025)
- [Why LLMs Cannot Think and How to Fix It](https://mlsanity.com/paper/2503.09211/) (2025)
- [The Non-Determinism of Small LLMs: Evidence of Low Answer Consistency in Repetition Trials of Standard Multiple-Choice Benchmarks](https://mlsanity.com/paper/2509.09705/) (2025)

## Abstract (arXiv)

Large language models are increasingly used as automated evaluators in research and enterprise settings, a practice known as LLM-as-a-judge. While prior work has examined accuracy, bias, and alignment with human preferences, far less attention has been given to how consistently LLMs assign numerical scores, an important concern for many production workflows. This study systematically evaluates scoring stability across five commonly used models, GPT-4o, GPT-4o-mini, Gemini-2.5-Flash, Claude-Haiku-4.5, and Claude-Sonnet-4.5, two temperature settings, and real enterprise question-answer pairs drawn from a retrieval-augmented generation (RAG) system. We address three questions: how stable a model's scores are across repeated runs, how differently models score identical inputs, and how temperature affects scoring consistency. Temperature controls the determinism of an LLM's output. Despite expectations of stability at temperature=0, we observe substantial variability across models, with completeness scoring showing the largest fluctuations. Cross-model comparisons reveal systematic differences in strictness and interpretive style, leading to divergent ratings for the same answers. Lower temperatures improve stability for some models, notably GPT-4o and Gemini, but have limited or inconsistent effects for Anthropic models. These findings have important implications for enterprise pipelines that rely on LLM-generated scores for routing, triage, gating, or quality control. Identical inputs can receive different scores depending on model, family, or temperature, raising concerns around fairness, reproducibility, and operational reliability. Our results highlight the need for monitoring, robust parsing, and hybrid human-LLM evaluation strategies to ensure dependable use of LLM-as-a-judge in production environments.