Gen-Verse/ReasonFlux

[NeurIPS 2025 Spotlight] LLM post-training suite — featuring ReasonFlux, ReasonFlux-PRM, and ReasonFlux-Coder.

34
/ 100
Emerging

This suite of models helps improve the advanced reasoning, coding, and problem-solving abilities of large language models (LLMs). It takes in existing LLMs or data related to their internal thought processes and outputs enhanced LLMs capable of more accurate long-form reasoning, robust code generation, and efficient problem-solving. This is for AI researchers, machine learning engineers, and developers working on building and deploying advanced LLM-powered applications.

524 stars. No commits in the last 6 months.

Use this if you are developing or fine-tuning large language models and need to significantly improve their capabilities in complex reasoning, reliable code generation, or structured problem-solving.

Not ideal if you are a non-technical end-user looking for a pre-built application, or if your primary focus is on simple text generation tasks that don't require deep reasoning or coding logic.

LLM fine-tuning AI model development Code generation Reinforcement learning for AI Complex problem solving
No License Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 10 / 25
Maturity 8 / 25
Community 14 / 25

How are scores calculated?

Stars

524

Forks

36

Language

Python

License

Last pushed

Sep 27, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/Gen-Verse/ReasonFlux"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.