Transparency signal for adopters, based on public metrics:
• Adoption: 91.9k GitHub stars (public metric)
• Maintenance: last push ~16 months ago
• Openness: weights + code fully public (MIT)
• Docs: official README, distill & deploy guides
Not a rating of the science.
⚠️ Red Flags & Trade-offs (AI Verified)
- The chain-of-thought can be bypassed — some prompts make the model emit a newline and skip reasoning; you must force it to start with a newline to trigger thinking reliably. [GitHub README]
- Reasoning models are verbose by design — even simple questions burn many tokens, so latency and cost run higher than non-reasoning models. [Nature]
- Distilled variants (built on Qwen / LLaMA bases) inherit those upstream licenses — they are not all pure MIT; check each distilled model's license file. [LICENSE]
Each flag links to its primary source. See our Correction Policy.
📝 Report a correction or complaint
Corrections and complaints go straight to our editorial queue — read and actioned by the site operator, not lost in an inbox. No email needed.
Open weights for DeepSeek's R1 reasoning model that rivals OpenAI o1, trained via large-scale reinforcement learning.
91.9k stars · 11.7k forks · last push Jun 2025
💡 Lighter Alternatives (If this is too heavy)
Disclaimer
Red Flags and the AI score are editorial analysis, not endorsements. They are produced with AI assistance and reviewed by a human, but are not a substitute for reading the primary source. Scores reflect public adoption and availability signals only — never a verdict on the science, the code quality, or the people behind a project. We are not affiliated with any lab, university, or company named on this page, and links point only at primary sources (papers, repositories, journals). Content is informational and not engineering, business, or investment advice.