ReasonBENCH: Benchmarking the (In)Stability of LLM Reasoning

• URL: http://arxiv.org/abs/2512.07795v1
• Date: Mon, 08 Dec 2025 18:26:58 GMT
• Title: ReasonBENCH: Benchmarking the (In)Stability of LLM Reasoning
• Authors: Nearchos Potamitis, Lars Klein, Akhil Arora,
• Abstract summary: We introduce ReasonBENCH, the first benchmark designed to quantify the underlying instability in large language models (LLMs) reasoning.<n>Across tasks from different domains, we find that the vast majority of reasoning strategies and models exhibit high instability.<n>We further analyze the impact of prompts, model families, and scale on the trade-off between solve rate and stability.
• Score: 2.1461777157838724
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large language models (LLMs) are increasingly deployed in settings where reasoning, such as multi-step problem solving and chain-of-thought, is essential. Yet, current evaluation practices overwhelmingly report single-run accuracy while ignoring the intrinsic uncertainty that naturally arises from stochastic decoding. This omission creates a blind spot because practitioners cannot reliably assess whether a method's reported performance is stable, reproducible, or cost-consistent. We introduce ReasonBENCH, the first benchmark designed to quantify the underlying instability in LLM reasoning. ReasonBENCH provides (i) a modular evaluation library that standardizes reasoning frameworks, models, and tasks, (ii) a multi-run protocol that reports statistically reliable metrics for both quality and cost, and (iii) a public leaderboard to encourage variance-aware reporting. Across tasks from different domains, we find that the vast majority of reasoning strategies and models exhibit high instability. Notably, even strategies with similar average performance can display confidence intervals up to four times wider, and the top-performing methods often incur higher and less stable costs. Such instability compromises reproducibility across runs and, consequently, the reliability of reported performance. To better understand these dynamics, we further analyze the impact of prompts, model families, and scale on the trade-off between solve rate and stability. Our results highlight reproducibility as a critical dimension for reliable LLM reasoning and provide a foundation for future reasoning methods and uncertainty quantification techniques. ReasonBENCH is publicly available at https://github.com/au-clan/ReasonBench .

Related papers

• STAR : Bridging Statistical and Agentic Reasoning for Large Model Performance Prediction [78.0692157478247]
  We propose STAR, a framework that bridges data-driven STatistical expectations with knowledge-driven Agentic Reasoning.<n>We show that STAR consistently outperforms all baselines on both score-based and rank-based metrics.
  arXiv  Detail & Related papers  (2026-02-12T16:30:07Z)
• Not All Preferences Are Created Equal: Stability-Aware and Gradient-Efficient Alignment for Reasoning Models [52.48582333951919]
  We propose a dynamic framework designed to enhance alignment reliability by maximizing the Signal-to-Noise Ratio of policy updates.<n>SAGE (Stability-Aware Gradient Efficiency) integrates a coarse-grained curriculum mechanism that refreshes candidate pools based on model competence.<n> Experiments on multiple mathematical reasoning benchmarks demonstrate that SAGE significantly accelerates convergence and outperforms static baselines.
  arXiv  Detail & Related papers  (2026-02-01T12:56:10Z)
• A Comprehensive Evaluation of LLM Reasoning: From Single-Model to Multi-Agent Paradigms [20.241519889633285]
  Large Language Models (LLMs) are increasingly deployed as reasoning systems, where reasoning paradigms play a critical role.<n>We conduct a comprehensive and unified evaluation of reasoning paradigms, spanning direct single-model generation, CoT-augmented single-model reasoning, and representative MAS.<n>We introduce MIMeBench, a new open-ended benchmark that targets two foundational yet underexplored semantic capabilities.
  arXiv  Detail & Related papers  (2026-01-19T17:23:45Z)
• Towards Comprehensive Stage-wise Benchmarking of Large Language Models in Fact-Checking [64.97768177044355]
  Large Language Models (LLMs) are increasingly deployed in real-world fact-checking systems.<n>We present FactArena, a fully automated arena-style evaluation framework.<n>Our analyses reveal significant discrepancies between static claim-verification accuracy and end-to-end fact-checking competence.
  arXiv  Detail & Related papers  (2026-01-06T02:51:56Z)
• Fact-Checking with Large Language Models via Probabilistic Certainty and Consistency [7.806516365113592]
  Large language models (LLMs) are increasingly used in applications requiring factual accuracy.<n>While fact-checking can mitigate these errors, existing methods typically retrieve external evidence indiscriminately.<n>We introduce Probabilistic Certainty and Consistency (PCC), a framework that estimates factual confidence.
  arXiv  Detail & Related papers  (2026-01-05T21:57:41Z)
• MaP: A Unified Framework for Reliable Evaluation of Pre-training Dynamics [72.00014675808228]
  Instability in Large Language Models evaluation process obscures true learning dynamics.<n>We introduce textbfMaP, a framework that integrates underlineMerging underlineand the underlinePass@k metric.<n>Experiments show that MaP yields significantly smoother performance curves, reduces inter-run variance, and ensures more consistent rankings.
  arXiv  Detail & Related papers  (2025-10-10T11:40:27Z)
• Deep Hidden Cognition Facilitates Reliable Chain-of-Thought Reasoning [33.30315111732609]
  Chain of Thought (CoT) reasoning has demonstrated remarkable deep reasoning capabilities.<n>However, its reliability is often undermined by the accumulation of errors in intermediate steps.<n>This paper introduces an approach to calibrate the CoT reasoning accuracy by leveraging the model's intrinsic veracity encoding.
  arXiv  Detail & Related papers  (2025-07-14T07:41:35Z)
• TokUR: Token-Level Uncertainty Estimation for Large Language Model Reasoning [27.449948943467163]
  We propose a Token-level Uncertainty estimation framework for Reasoning (TokUR)<n>TokUR enables Large Language Models to self-assess and self-improve their responses in mathematical reasoning.<n> Experiments on mathematical reasoning datasets of varying difficulty demonstrate that TokUR exhibits a strong correlation with answer correctness and model robustness.
  arXiv  Detail & Related papers  (2025-05-16T22:47:32Z)
• ConCISE: Confidence-guided Compression in Step-by-step Efficient Reasoning [64.93140713419561]
  Large Reasoning Models (LRMs) perform strongly in complex reasoning tasks via Chain-of-Thought (CoT) prompting, but often suffer from verbose outputs.<n>Existing fine-tuning-based compression methods either operate post-hoc pruning, risking disruption to reasoning coherence, or rely on sampling-based selection.<n>We introduce ConCISE, a framework designed to generate concise reasoning chains, integrating Confidence Injection to boost reasoning confidence, and Early Stopping to terminate reasoning when confidence is sufficient.
  arXiv  Detail & Related papers  (2025-05-08T01:40:40Z)
• Enhancing LLM Reliability via Explicit Knowledge Boundary Modeling [41.19330514054401]
  Large language models (LLMs) are prone to hallucination stemming from misaligned self-awareness.<n>We propose the Explicit Knowledge Boundary Modeling framework to integrate fast and slow reasoning systems to harmonize reliability and usability.
  arXiv  Detail & Related papers  (2025-03-04T03:16:02Z)
• Bridging Internal Probability and Self-Consistency for Effective and Efficient LLM Reasoning [53.25336975467293]
  We present the first theoretical error decomposition analysis of methods such as perplexity and self-consistency.<n>Our analysis reveals a fundamental trade-off: perplexity methods suffer from substantial model error due to the absence of a proper consistency function.<n>We propose Reasoning-Pruning Perplexity Consistency (RPC), which integrates perplexity with self-consistency, and Reasoning Pruning, which eliminates low-probability reasoning paths.
  arXiv  Detail & Related papers  (2025-02-01T18:09:49Z)
• Cycles of Thought: Measuring LLM Confidence through Stable Explanations [53.15438489398938]
  Large language models (LLMs) can reach and even surpass human-level accuracy on a variety of benchmarks, but their overconfidence in incorrect responses is still a well-documented failure mode. We propose a framework for measuring an LLM's uncertainty with respect to the distribution of generated explanations for an answer.
  arXiv  Detail & Related papers  (2024-06-05T16:35:30Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.