# Are Your LLMs Capable of Stable Reasoning?

arXiv: https://arxiv.org/abs/2412.13147 · HTML: https://mlsanity.com/paper/2412.13147/

## Key facts

- Cited by 65 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning.
- Builds on 21 of its 41 references that are in the map.
- First posted on arXiv 17 Dec 2024.

## Placed in

- LLM reasoning / [Reasoning benchmarks and evaluation](https://mlsanity.com/lr/reasoning-benchmarks-and-evaluation/)

## Builds on (most cited first, 21 of 21)

- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [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)
- [Measuring Mathematical Problem Solving With the MATH Dataset](https://mlsanity.com/paper/2103.03874/) (2021)
- [Let's Verify Step by Step](https://mlsanity.com/paper/2305.20050/) (2023)
- [Gemma 2: Improving Open Language Models at a Practical Size](https://mlsanity.com/paper/2408.00118/) (2024)
- [Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters](https://mlsanity.com/paper/2408.03314/) (2024)
- [τ-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains](https://mlsanity.com/paper/2406.12045/) (2024)
- [Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement](https://mlsanity.com/paper/2409.12122/) (2024)
- [WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instruct](https://mlsanity.com/paper/2308.09583/) (2023)
- [Explain Yourself! Leveraging Language Models for Commonsense Reasoning](https://mlsanity.com/paper/1906.02361/) (2019)
- [Out-of-Distribution Detection and Selective Generation for Conditional Language Models](https://mlsanity.com/paper/2209.15558/) (2022)
- [Don't Make Your LLM an Evaluation Benchmark Cheater](https://mlsanity.com/paper/2311.01964/) (2023)
- [SPoC: Search-based Pseudocode to Code](https://mlsanity.com/paper/1906.04908/) (2019)
- [ProSA: Assessing and Understanding the Prompt Sensitivity of LLMs](https://mlsanity.com/paper/2410.12405/) (2024)
- [InternLM-Math: Open Math Large Language Models Toward Verifiable Reasoning](https://mlsanity.com/paper/2402.06332/) (2024)
- [MathBench: Evaluating the Theory and Application Proficiency of LLMs with a Hierarchical Mathematics Benchmark](https://mlsanity.com/paper/2405.12209/) (2024)
- [Latent Space Chain-of-Embedding Enables Output-free LLM Self-Evaluation](https://mlsanity.com/paper/2410.13640/) (2024)
- [Changing Answer Order Can Decrease MMLU Accuracy](https://mlsanity.com/paper/2406.19470/) (2024)
- [LLM-as-a-Judge & Reward Model: What They Can and Cannot Do](https://mlsanity.com/paper/2409.11239/) (2024)

## Built on by (most cited first, 30 of 65)

- [SDAR: A Synergistic Diffusion-AutoRegression Paradigm for Scalable Sequence Generation](https://mlsanity.com/paper/2510.06303/) (2025)
- [The Invisible Leash: Why RLVR May or May Not Escape Its Origin](https://mlsanity.com/paper/2507.14843/) (2025)
- [Efficient Reasoning Models: A Survey](https://mlsanity.com/paper/2504.10903/) (2025)
- [A Sober Look at Progress in Language Model Reasoning: Pitfalls and Paths to Reproducibility](https://mlsanity.com/paper/2504.07086/) (2025)
- [Reasoning or Memorization? Unreliable Results of Reinforcement Learning Due to Data Contamination](https://mlsanity.com/paper/2507.10532/) (2025)
- [xVerify: Efficient Answer Verifier for Reasoning Model Evaluations](https://mlsanity.com/paper/2504.10481/) (2025)
- [Exploring the Limit of Outcome Reward for Learning Mathematical Reasoning](https://mlsanity.com/paper/2502.06781/) (2025)
- [CompassVerifier: A Unified and Robust Verifier for LLMs Evaluation and Outcome Reward](https://mlsanity.com/paper/2508.03686/) (2025)
- [The Avengers: A Simple Recipe for Uniting Smaller Language Models to Challenge Proprietary Giants](https://mlsanity.com/paper/2505.19797/) (2025)
- [LLMRouterBench: A Massive Benchmark and Unified Framework for LLM Routing](https://mlsanity.com/paper/2601.07206/) (2026)
- [R-Bench: Graduate-level Multi-disciplinary Benchmarks for LLM & MLLM Complex Reasoning Evaluation](https://mlsanity.com/paper/2505.02018/) (2025)
- [Learn Globally, Speak Locally: Bridging the Gaps in Multilingual Reasoning](https://mlsanity.com/paper/2507.05418/) (2025)
- [Solving Inequality Proofs with Large Language Models](https://mlsanity.com/paper/2506.07927/) (2025)
- [InternBootcamp: Boosting LLM Reasoning with Verifiable Task Scaling](https://mlsanity.com/paper/2508.08636/) (2025)
- [LLMs Provide Unstable Answers to Legal Questions](https://mlsanity.com/paper/2502.05196/) (2025)
- [Don't Pass@k: A Bayesian Framework for Large Language Model Evaluation](https://mlsanity.com/paper/2510.04265/) (2025)
- [Spurious Rewards Paradox: Mechanistically Understanding How RLVR Activates Memorization Shortcuts in LLMs](https://mlsanity.com/paper/2601.11061/) (2026)
- [No Need for Explanations: LLMs can implicitly learn from mistakes in-context](https://mlsanity.com/paper/2502.08550/) (2025)
- [Position: The Hidden Costs and Measurement Gaps of Reinforcement Learning with Verifiable Rewards](https://mlsanity.com/paper/2509.21882/) (2025)
- [CipherBank: Exploring the Boundary of LLM Reasoning Capabilities through Cryptography Challenges](https://mlsanity.com/paper/2504.19093/) (2025)
- [Parallelism and Generation Order in Masked Diffusion Language Models: Limits Today, Potential Tomorrow](https://mlsanity.com/paper/2601.15593/) (2026)
- [Ring-lite: Scalable Reasoning via C3PO-Stabilized Reinforcement Learning for LLMs](https://mlsanity.com/paper/2506.14731/) (2025)
- [Every Attention Matters: An Efficient Hybrid Architecture for Long-Context Reasoning](https://mlsanity.com/paper/2510.19338/) (2025)
- [SafeLawBench: Towards Safe Alignment of Large Language Models](https://mlsanity.com/paper/2506.06636/) (2025)
- [Beyond Pass@k: Breadth-Depth Metrics for Reasoning Boundaries](https://mlsanity.com/paper/2510.08325/) (2025)
- [ReasonBENCH: Benchmarking the (In)Stability of LLM Reasoning](https://mlsanity.com/paper/2512.07795/) (2025)
- [Solve-Detect-Verify: Inference-Time Scaling with Flexible Generative Verifier](https://mlsanity.com/paper/2505.11966/) (2025)
- [Has the Creativity of Large-Language Models peaked? An analysis of inter- and intra-LLM variability](https://mlsanity.com/paper/2504.12320/) (2025)
- [Cooper: Co-Optimizing Policy and Reward Models in Reinforcement Learning for Large Language Models](https://mlsanity.com/paper/2508.05613/) (2025)
- [SCI-Verifier: Scientific Verifier with Thinking](https://mlsanity.com/paper/2509.24285/) (2025)

## Abstract (arXiv)

The rapid advancement of large language models (LLMs) has shown remarkable progress in complex reasoning tasks. However, a significant disparity exists between benchmark performances and real-world applications. We attribute this gap primarily to current evaluation protocols and metrics, which inadequately capture the full spectrum of LLM capabilities, especially in complex reasoning tasks where both accuracy and consistency are essential. In this paper, we introduce G-Pass@k, a novel evaluation metric that continuously assesses model performance across multiple sampling attempts, quantifying both the model's performance potential and its stability. Through extensive experiments on various public and newly constructed benchmarks, we employ G-Pass@k in conjunction with state-of-the-art large language models to provide comprehensive insights into their potential capabilities and operational consistency. Our findings reveal a significant opportunity to enhance the realistic reasoning abilities of LLMs, underscoring the necessity for more robust evaluation metrics.