mlsanityData to 14 Oct 2026

EasyMath: A 0-shot Math Benchmark for SLMs

arXiv 2505.14852 ↗First posted 20 May 2025cs.CL cs.AI cs.LGcited by 0

On the map: LLM reasoning → Mathematical reasoning

Abstract (arXiv)

EasyMath is a compact benchmark for practical math reasoning in small language models. It covers thirteen categories, from basic arithmetic and order of operations to word problems, algebraic expressions, edge cases, and omits specialist topics. We tested 23 models (14M to 4B parameters) using exact, numerical, and symbolic checks on free-form answers in a zero-shot setting. Accuracy rises with size and training, chain-of-thought adds modest gains, and consistency improves at scale.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Mathematical reasoning, one of 17 directions in LLM reasoning. Builds on 18 of its 28 references that are in the map. First posted on arXiv 20 May 2025.

Builds on

18 of 28 references.

Closest ancestors · 2

Same direction, newest first

  1. 2024HARP: A challenging human-annotated math reasoning benchmark11 Dec
  2. 2024Small Language Models are Equation Reasoners19 Sep

Other references · 16

  1. 2015Distilling the Knowledge in a Neural Networkcited by 10,324
  2. 2021Training Verifiers to Solve Math Word Problemscited by 10,109
  3. 2021Measuring Mathematical Problem Solving With the MATH Datasetcited by 5,371
  4. 2022Large Language Models are Zero-Shot Reasonerscited by 4,374
  5. 2023Let's Verify Step by Stepcited by 3,789
  6. 2023Pythia: A Suite for Analyzing Large Language Models Across Training and Scalingcited by 1,786
  7. 2024Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvementcited by 1,090
  8. 2019MathQA: Towards Interpretable Math Word Problem Solving with Operation-Based Formalismscited by 662
  9. 2025Small Models Struggle to Learn from Strong Reasonerscited by 113
  10. 2024Chain of Preference Optimization: Improving Chain-of-Thought Reasoning in LLMscited by 96
  11. 2024Calibrating Large Language Models with Sample Consistencycited by 73
  12. 2025Think Smarter not Harder: Adaptive Reasoning with Inference Aware Optimizationcited by 29
4 more
  1. 2025Towards Reasoning Ability of Small Language Modelscited by 29
  2. 2024Why do small language models underperform? Studying Language Model Saturation via the Softmax Bottleneckcited by 21
  3. 2025Assessing Consistency and Reproducibility in the Outputs of Large Language Models: Evidence Across Diverse Finance and Accounting Taskscited by 20
  4. 2024SmolTulu: Higher Learning Rate to Batch Size Ratios Can Lead to Better Reasoning in SLMscited by 3

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024UTMath: Math Evaluation with Unit Test via Reasoning-to-Coding Thoughts
  2. 2025Challenging the Boundaries of Reasoning: An Olympiad-Level Math Benchmark for Large Language Models
  3. 2025Do LLMs Overthink Basic Math Reasoning? Benchmarking the Accuracy-Efficiency Tradeoff in Language Models
  4. 2023MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models
  5. 2024PARAMANU-GANITA: Can Small Math Language Models Rival with Large Language Models on Mathematical Reasoning?
  6. 2024ConceptMath: A Bilingual Concept-wise Benchmark for Measuring Mathematical Reasoning of Large Language Models
  7. 2025FormalMATH: Benchmarking Formal Mathematical Reasoning of Large Language Models
  8. 2025BrokenMath: A Benchmark for Sycophancy in Theorem Proving with LLMs