ARCHIVES
Year 2026 · Volume 5 · Issue 3
Original Article
Model Scale versus Search in Novel Mathematical Problem Solving: An Exploratory Comparison of Ministral 3.5 and GPT Frontier Models
Anirudh Khajuria1
1 Indian Institute of Forest Management Bhopal (MBA -FM 25-27) Electrical Engineering (UNIVERSITY OF JAMMU), Jammu and Kashmir.
Published Online: September-December 2026
Pages: 243-247
Cite this article
↗ https://www.doi.org/10.59256/indjcst.20260503029
References
1. Kaplan, J., et al. (2020). Scaling Laws for Neural Language Models.
2. Hoffmann, J., et al. (2022). Training Compute-Optimal Large Language Models.
3. Wang, X., et al. (2022). Self-Consistency Improves Chain of Thought Reasoning in Language Models.
4. Yao, S., et al. (2023). Tree of Thoughts: Deliberate Problem Solving with Large Language Models.
5. Cobbe, K., et al. (2021). Training Verifiers to Solve Math Word Problems.
6. Lightman, H., et al. (2023). Let's Verify Step by Step.
7. Snell, C., et al. (2024). Scaling LLM Test-Time Compute Optimally Can Be More Effective Than Scaling Model Parameters.
8. Muennighoff, N., et al. (2025). s1: Simple Test-Time Scaling.
9. DeepSeek-AI et al. (2025). DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning.
10. Trinh, T. H., & Luong, T. (2024). AlphaGeometry; Glazer, E., et al. (2024). FrontierMath.
11. Guan, X., Zhang, L. L., Liu, Y., et al. (2025). rStar-Math: Small LLMs Can Master Math Reasoning with Self-Evolved Deep Thinking. arXiv:2501.04519 (ICML 2025).
2. Hoffmann, J., et al. (2022). Training Compute-Optimal Large Language Models.
3. Wang, X., et al. (2022). Self-Consistency Improves Chain of Thought Reasoning in Language Models.
4. Yao, S., et al. (2023). Tree of Thoughts: Deliberate Problem Solving with Large Language Models.
5. Cobbe, K., et al. (2021). Training Verifiers to Solve Math Word Problems.
6. Lightman, H., et al. (2023). Let's Verify Step by Step.
7. Snell, C., et al. (2024). Scaling LLM Test-Time Compute Optimally Can Be More Effective Than Scaling Model Parameters.
8. Muennighoff, N., et al. (2025). s1: Simple Test-Time Scaling.
9. DeepSeek-AI et al. (2025). DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning.
10. Trinh, T. H., & Luong, T. (2024). AlphaGeometry; Glazer, E., et al. (2024). FrontierMath.
11. Guan, X., Zhang, L. L., Liu, Y., et al. (2025). rStar-Math: Small LLMs Can Master Math Reasoning with Self-Evolved Deep Thinking. arXiv:2501.04519 (ICML 2025).
Related Articles
2026
Artificial Intelligence in Learning and Teaching
2026
Admin Assist: An AI – Driven Configuration and Orchestration for Enterprise Application
2026
Enhancing Blood Group Identification using pigeon inspired optimization: An Innovative Approach
2026
Eco-Genius: Power Up Smart, Power Down Waste
2026
Crowd-Sourced Disaster Response and Rescue Assistant
2026
Unveiling Deepfake Detection Using Vision Transformers: A Survey and Experimental Study
Share Article
Or copy link
https://www.indjcst.com/archives/model-scale-versus-search-in-novel-mathematical-problem-solving-an-exploratory-comparison-of-ministral-35-and-gpt-frontier-models
*Instagram doesn't support direct link sharing from web. Copy the link and share it in your Instagram story or post.