# Towards Reasoning Ability of Small Language Models

arXiv: https://arxiv.org/abs/2502.11569 · HTML: https://mlsanity.com/paper/2502.11569/

## Key facts

- Cited by 29 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning.
- Builds on 34 of its 43 references that are in the map.
- First posted on arXiv 17 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 34)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Measuring Mathematical Problem Solving With the MATH Dataset](https://mlsanity.com/paper/2103.03874/) (2021)
- [PaLM: Scaling Language Modeling with Pathways](https://mlsanity.com/paper/2204.02311/) (2022)
- [Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge](https://mlsanity.com/paper/1803.05457/) (2018)
- [HellaSwag: Can a Machine Really Finish Your Sentence?](https://mlsanity.com/paper/1905.07830/) (2019)
- [Finetuned Language Models Are Zero-Shot Learners](https://mlsanity.com/paper/2109.01652/) (2021)
- [Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering](https://mlsanity.com/paper/1809.02789/) (2018)
- [CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge](https://mlsanity.com/paper/1811.00937/) (2018)
- [Knowledge Distillation: A Survey](https://mlsanity.com/paper/2006.05525/) (2020)
- [A Survey on LLM-as-a-Judge](https://mlsanity.com/paper/2411.15594/) (2024)
- [Large Language Models Cannot Self-Correct Reasoning Yet](https://mlsanity.com/paper/2310.01798/) (2023)
- [Can Large Language Models Be an Alternative to Human Evaluations?](https://mlsanity.com/paper/2305.01937/) (2023)
- [MathQA: Towards Interpretable Math Word Problem Solving with Operation-Based Formalisms](https://mlsanity.com/paper/1905.13319/) (2019)
- [Is ChatGPT a Good NLG Evaluator? A Preliminary Study](https://mlsanity.com/paper/2303.04048/) (2023)
- [rStar-Math: Small LLMs Can Master Math Reasoning with Self-Evolved Deep Thinking](https://mlsanity.com/paper/2501.04519/) (2025)
- [Teaching Small Language Models to Reason](https://mlsanity.com/paper/2212.08410/) (2022)
- [Specializing Smaller Language Models towards Multi-Step Reasoning](https://mlsanity.com/paper/2301.12726/) (2023)
- [Judging the Judges: Evaluating Alignment and Vulnerabilities in LLMs-as-Judges](https://mlsanity.com/paper/2406.12624/) (2024)
- [Orca 2: Teaching Small Language Models How to Reason](https://mlsanity.com/paper/2311.11045/) (2023)
- [Towards Understanding Knowledge Distillation](https://mlsanity.com/paper/2105.13093/) (2021)
- [Multi-Step Reasoning with Large Language Models, a Survey](https://mlsanity.com/paper/2407.11511/) (2024)
- [A Comprehensive Survey of Small Language Models in the Era of Large Language Models: Techniques, Enhancements, Applications, Collaboration with LLMs, and Trustworthiness](https://mlsanity.com/paper/2411.03350/) (2024)
- [Small Language Models: Survey, Measurements, and Insights](https://mlsanity.com/paper/2409.15790/) (2024)
- [Hymba: A Hybrid-head Architecture for Small Language Models](https://mlsanity.com/paper/2411.13676/) (2024)
- [Small Language Models Need Strong Verifiers to Self-Correct Reasoning](https://mlsanity.com/paper/2404.17140/) (2024)
- [OpenELM: An Efficient Language Model Family with Open Training and Inference Framework](https://mlsanity.com/paper/2404.14619/) (2024)
- [MR-GSM8K: A Meta-Reasoning Benchmark for Large Language Model Evaluation](https://mlsanity.com/paper/2312.17080/) (2023)
- [Evaluation Metrics in the Era of GPT-4: Reliably Evaluating Large Language Models on Sequence to Sequence Tasks](https://mlsanity.com/paper/2310.13800/) (2023)

## Built on by (most cited first, 29 of 29)

- [Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models](https://mlsanity.com/paper/2503.16419/) (2025)
- [Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models](https://mlsanity.com/paper/2503.09567/) (2025)
- [Thinkless: LLM Learns When to Think](https://mlsanity.com/paper/2505.13379/) (2025)
- [Efficient Reasoning Models: A Survey](https://mlsanity.com/paper/2504.10903/) (2025)
- [Speculative Thinking: Enhancing Small-Model Reasoning with Large Model Guidance at Inference Time](https://mlsanity.com/paper/2504.12329/) (2025)
- [Multimodal Spatial Reasoning in the Large Model Era: A Survey and Benchmarks](https://mlsanity.com/paper/2510.25760/) (2025)
- [VeriThinker: Learning to Verify Makes Reasoning Model Efficient](https://mlsanity.com/paper/2505.17941/) (2025)
- [StreamingThinker: Large Language Models Can Think While Reading](https://mlsanity.com/paper/2510.17238/) (2025)
- [When Reasoning Meets Compression: Understanding the Effects of LLMs Compression on Large Reasoning Models](https://mlsanity.com/paper/2504.02010/) (2025)
- [DeepPrune: Parallel Scaling without Inter-trace Redundancy](https://mlsanity.com/paper/2510.08483/) (2025)
- [What Makes Low-Bit Quantization-Aware Training Work for Reasoning LLMs? A Systematic Study](https://mlsanity.com/paper/2601.14888/) (2026)
- [Table-r1: Self-supervised and Reinforcement Learning for Program-based Table Reasoning in Small Language Models](https://mlsanity.com/paper/2506.06137/) (2025)
- [DEBATE, TRAIN, EVOLVE: Self Evolution of Language Model Reasoning](https://mlsanity.com/paper/2505.15734/) (2025)
- [RuleReasoner: Reinforced Rule-based Reasoning via Domain-aware Dynamic Sampling](https://mlsanity.com/paper/2506.08672/) (2025)
- [Do LLMs Overthink Basic Math Reasoning? Benchmarking the Accuracy-Efficiency Tradeoff in Language Models](https://mlsanity.com/paper/2507.04023/) (2025)
- [Reasoning Scaffolding: Distilling the Flow of Thought from LLMs](https://mlsanity.com/paper/2509.23619/) (2025)
- [Mixed-Precision Quantization for Language Models: Techniques and Prospects](https://mlsanity.com/paper/2510.16805/) (2025)
- [Efficient Reasoning with Balanced Thinking](https://mlsanity.com/paper/2603.12372/) (2026)
- [Investigating Language Model Capabilities to Represent and Process Formal Knowledge: A Preliminary Study to Assist Ontology Engineering](https://mlsanity.com/paper/2509.10249/) (2025)
- [DICE: Structured Reasoning in LLMs through SLM-Guided Chain-of-Thought Correction](https://mlsanity.com/paper/2510.09211/) (2025)
- [QA-Merging: Query-Adaptive Reasoning via Layer Selective Model Merging](https://mlsanity.com/paper/2601.03506/) (2026)
- [When Correct Isn't Usable: Improving Structured Output Reliability in Small Language Models](https://mlsanity.com/paper/2605.02363/) (2026)
- [EasyMath: A 0-shot Math Benchmark for SLMs](https://mlsanity.com/paper/2505.14852/) (2025)
- [Dissecting Physics Reasoning in Small Language Models: A Multi-Dimensional Analysis from an Educational Perspective](https://mlsanity.com/paper/2505.20707/) (2025)
- [Fast Reasoning Segmentation for Images and Videos](https://mlsanity.com/paper/2511.12368/) (2025)
- [WRAVAL -- WRiting Assist eVALuation](https://mlsanity.com/paper/2601.03268/) (2025)
- [BoostTaxo: Zero-Shot Taxonomy Induction via Boosting-Style Agentic Reasoning and Constraint-Aware Calibration](https://mlsanity.com/paper/2605.12520/) (2026)
- [Quantum-Inspired Trace-Augmented Evidence Selection for Reasoning over Structured Hypothesis Spaces](https://mlsanity.com/paper/2606.06941/) (2026)
- [Enhancing SLMs for Sustainable Code Optimization in Radio-Astronomy](https://mlsanity.com/paper/2607.21677/) (2026)

## Abstract (arXiv)

Reasoning has long been viewed as an emergent property of large language models (LLMs). However, recent studies challenge this assumption, showing that small language models (SLMs) can also achieve competitive reasoning performance. This paper introduces ThinkSLM, the first extensive benchmark to systematically evaluate and study the reasoning abilities of SLMs trained from scratch or derived from LLMs through quantization, pruning, and distillation. We first establish a reliable evaluation criterion comparing available methods and LLM judges against our human evaluations. Then we present a study evaluating 72 diverse SLMs from six major model families across 17 reasoning benchmarks. We repeat all our experiments three times to ensure a robust assessment. Our findings show that: 1) reasoning ability in SLMs is strongly influenced by training methods and data quality rather than solely model scale; 2) quantization preserves reasoning capability, while pruning significantly disrupts it; 3) larger models consistently exhibit higher robustness against adversarial perturbations and intermediate reasoning, but certain smaller models closely match or exceed the larger models' performance. Our findings challenge the assumption that scaling is the only way to achieve strong reasoning. Instead, we foresee a future where SLMs with strong reasoning capabilities can be developed through structured training or post-training compression. Our ThinkSLM Leaderboard is publicly available at: https://ctrl-gaurav.github.io/thinkslm.github.io/