# ThinkBench: Dynamic Out-of-Distribution Evaluation for Robust LLM Reasoning

arXiv: https://arxiv.org/abs/2502.16268 · HTML: https://mlsanity.com/paper/2502.16268/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning.
- Builds on 38 of its 71 references that are in the map.
- First posted on arXiv 22 Feb 2025.

## Placed in

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

## Builds on (most cited first, 30 of 38)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [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)
- [Mistral 7B](https://mlsanity.com/paper/2310.06825/) (2023)
- [GPQA: A Graduate-Level Google-Proof Q&A Benchmark](https://mlsanity.com/paper/2311.12022/) (2023)
- [Mixtral of Experts](https://mlsanity.com/paper/2401.04088/) (2024)
- [s1: Simple test-time scaling](https://mlsanity.com/paper/2501.19393/) (2025)
- [Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement](https://mlsanity.com/paper/2409.12122/) (2024)
- [Solving math word problems with process- and outcome-based feedback](https://mlsanity.com/paper/2211.14275/) (2022)
- [Reasoning with Language Model is Planning with World Model](https://mlsanity.com/paper/2305.14992/) (2023)
- [DeepSeek-V3 Technical Report](https://mlsanity.com/paper/2412.19437/) (2024)
- [A Comprehensive Overview of Large Language Models](https://mlsanity.com/paper/2307.06435/) (2023)
- [Generative Verifiers: Reward Modeling as Next-Token Prediction](https://mlsanity.com/paper/2408.15240/) (2024)
- [The Lessons of Developing Process Reward Models in Mathematical Reasoning](https://mlsanity.com/paper/2501.07301/) (2025)
- [PandaLM: An Automatic Evaluation Benchmark for LLM Instruction Tuning Optimization](https://mlsanity.com/paper/2306.05087/) (2023)
- [ProcessBench: Identifying Process Errors in Mathematical Reasoning](https://mlsanity.com/paper/2412.06559/) (2024)
- [Making Large Language Models Better Reasoners with Step-Aware Verifier](https://mlsanity.com/paper/2206.02336/) (2022)
- [On the Robustness of ChatGPT: An Adversarial and Out-of-distribution Perspective](https://mlsanity.com/paper/2302.12095/) (2023)
- [GSM-Plus: A Comprehensive Benchmark for Evaluating the Robustness of LLMs as Mathematical Problem Solvers](https://mlsanity.com/paper/2402.19255/) (2024)
- [Holistic Evaluation of Language Models](https://mlsanity.com/paper/2211.09110/) (2022)
- [Evaluation of OpenAI o1: Opportunities and Challenges of AGI](https://mlsanity.com/paper/2409.18486/) (2024)
- [OpenR: An Open Source Framework for Advanced Reasoning with Large Language Models](https://mlsanity.com/paper/2410.09671/) (2024)
- [O1 Replication Journey -- Part 2: Surpassing O1-preview through Simple Distillation, Big Progress or Bitter Lesson?](https://mlsanity.com/paper/2411.16489/) (2024)
- [Dynamic Evaluation of Large Language Models by Meta Probing Agents](https://mlsanity.com/paper/2402.14865/) (2024)

## Built on by (most cited first, 17 of 17)

- [Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models](https://mlsanity.com/paper/2503.09567/) (2025)
- [From System 1 to System 2: A Survey of Reasoning Large Language Models](https://mlsanity.com/paper/2502.17419/) (2025)
- [Trade-offs in Large Reasoning Models: An Empirical Analysis of Deliberative and Adaptive Reasoning over Foundational Capabilities](https://mlsanity.com/paper/2503.17979/) (2025)
- [ReasonBENCH: Benchmarking the (In)Stability of LLM Reasoning](https://mlsanity.com/paper/2512.07795/) (2025)
- [BeyondBench: Contamination-Resistant Evaluation of Reasoning in Language Models](https://mlsanity.com/paper/2509.24210/) (2025)
- [Enhancing Large Language Model Reasoning with Reward Models: An Analytical Survey](https://mlsanity.com/paper/2510.01925/) (2025)
- [Loki's Dance of Illusions: A Comprehensive Survey of Hallucination in Large Language Models](https://mlsanity.com/paper/2507.02870/) (2025)
- [The Thin Line Between Comprehension and Persuasion in LLMs](https://mlsanity.com/paper/2507.01936/) (2025)
- [MCEval: A Dynamic Framework for Fair Multilingual Cultural Evaluation of LLMs](https://mlsanity.com/paper/2507.09701/) (2025)
- [SATQuest: A Verifier for Logical Reasoning Evaluation and Reinforcement Fine-Tuning of LLMs](https://mlsanity.com/paper/2509.00930/) (2025)
- [RefuteBench 2.0 -- Agentic Benchmark for Dynamic Evaluation of LLM Responses to Refutation Instruction](https://mlsanity.com/paper/2502.18308/) (2025)
- [Prompting Test-Time Scaling Is A Strong LLM Reasoning Data Augmentation](https://mlsanity.com/paper/2510.09599/) (2025)
- [Foundation models may exhibit staged progression in novel CBRN threat disclosure](https://mlsanity.com/paper/2503.15182/) (2025)
- [Advances in LLM Reasoning Enable Flexibility in Clinical Problem-Solving](https://mlsanity.com/paper/2601.11866/) (2026)
- [Silicon Bureaucracy and AI Test-Oriented Education: Contamination Sensitivity and Score Confidence in LLM Benchmarks](https://mlsanity.com/paper/2603.21636/) (2026)
- [The Generalization Spectrum: A Chromatographic Approach to Evaluating Learning Algorithms](https://mlsanity.com/paper/2606.25450/) (2026)
- [Semifactual Credit-Augmented Policy Optimization](https://mlsanity.com/paper/2609.40360/) (2026)

## Abstract (arXiv)

Evaluating large language models (LLMs) poses significant challenges, particularly due to issues of data contamination and the leakage of correct answers. To address these challenges, we introduce ThinkBench, a novel evaluation framework designed to evaluate LLMs' reasoning capability robustly. ThinkBench proposes a dynamic data generation method for constructing out-of-distribution (OOD) datasets and offers an OOD dataset that contains 2,912 samples drawn from reasoning tasks. ThinkBench unifies the evaluation of reasoning models and non-reasoning models. We evaluate 16 LLMs and 4 PRMs under identical experimental conditions and show that most of the LLMs' performance are far from robust and they face a certain level of data leakage. By dynamically generating OOD datasets, ThinkBench effectively provides a reliable evaluation of LLMs and reduces the impact of data contamination.