Discussion - Topic: Reasoning models

This week's topic: Reasoning models

As described in Thoughtworks Technology Radar Vol. #32.

One of the most significant AI advances since the last Radar is the breakthrough and proliferation of reasoning models. Also marketed as “thinking models,” these models have achieved top human-level performance in benchmarks like frontier mathematics and coding.

Reasoning models are usually trained through reinforcement learning or supervised fine-tuning, enhancing capabilities such as step-by-step thinking (CoT), exploring alternatives (ToT) and self-correction. Examples include OpenAI’s o1/o3, DeepSeek R1 and Gemini 2.0 Flash Thinking. However, these models should be seen as a distinct category of LLMs rather than simply more advanced versions.

This increased capability comes at a cost. Reasoning models require longer response time and higher token consumption, leading us to jokingly call them “Slower AI” (as if current AI wasn’t slow enough). Not all tasks justify this trade-off. For simpler tasks like text summarization, content generation or fast-response chatbots, general-purpose LLMs remain the better choice. We advise using reasoning models in STEM fields, complex problem-solving and decision-making — for example, when using LLMs as judges or improving explainability through explicit CoT outputs. At the time of writing, Claude 3.7 Sonnet, a hybrid reasoning model, had just been released, hinting at a possible fusion between traditional LLMs and reasoning models.

Zoom link will be added about 5 min before the event starts.

Discussion Resources :

Please try to read/watch before the meetup as it will help drive the discussions.
Understanding Reasoning LLMs by Sebastian Raschka, PhD
https://magazine.sebastianraschka.com/p/understanding-reasoning-llms

5 Best AI Reasoning Models of 2025: Ranked! by Raman Thakur
https://www.labellerr.com/blog/compare-reasoning-models/

The Rise of Reasoning Models: How AI is Learning to Think Step by Step by GÁBOR HORVÁTH
https://hiflylabs.com/blog/2025/4/3/reasoning-models

Top 5 Reasoning Models to Use in 2025: Speed, Specialty & What’s Next by Jatin Garg
https://www.gocodeo.com/post/top-5-reasoning-models-to-use-in-2025-speed-specialty-whats-next

Reasoning Models Explained: What They Are, How They Work, and When to Use Them Over Traditional LLMs by Adam Lieberman
https://dzone.com/articles/reasoning-models-vs-llms-guide