DeepSeek-R1 is an open-weights reasoning model released by DeepSeek on 22 January 2025. It is built on the DeepSeek-V3 base and was published as arXiv 2501.12948 and later in Nature 645, 633–638 (2025). The model demonstrated frontier-competitive reasoning at lower training compute than leading US models and became a reference case in debates over fast-follow competition, distillation, and open-weights release.
| Field | Value | |
|---|---|---|
| Developer | [[deepseek-company | DeepSeek]] |
| Released | January 2025 | |
| Type | Open-weights reasoning model | |
| License | Open-weight | |
| Base | DeepSeek-V3 | |
| Key innovations | Pure-RL reasoning emergence (R1-Zero); multi-stage cold-start + RL (R1); distillation into 1.5B–70B dense models | |
| Publication | arXiv 2501.12948; Nature 645, 633–638 (2025) |
Capabilities and benchmarks
In February 2025 DeepSeek-R1 briefly matched the top US model, OpenAI's o1, an event an Epoch AI account described as "driving the stock market bananas" (Source: epochai.substack.com). It showed that compute-poor labs could reach frontier-competitive reasoning performance using less training compute.
Training and architecture
The R1 paper (DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning) introduces two training regimes:
- R1-Zero — pure reinforcement learning (RL) from a base model with no supervised fine-tuning (SFT). Reasoning behaviors such as self-reflection, verification, and long chain-of-thought emerge from RL with rule-based rewards. The paper's central claim is that reasoning does not require human-labeled reasoning trajectories.
- R1 — adds a cold-start SFT stage and multi-stage RL to fix the readability and language-mixing issues seen in R1-Zero.
The paper frames the reasoning-capability axis as a question of RL compute rather than pre-training compute, a framing relevant to Scaling Laws.
Publication and peer review
The R1 paper appeared on the cover of Nature on September 18, 2025 (vol. 645, issue 8081, pp. 633–638), following formal peer review — coverage of the publication described R1 as the first mainstream large language model to pass through journal peer review (Source: nature.com; eu.36kr.com). Supplementary material published with the paper disclosed that the R1 reasoning-stage training cost was $294,000 in compute (on top of the base-model cost), a figure widely cited as far below the reported training costs of comparable US models (Source: mlq.ai).
Open weights and distillation
DeepSeek-R1 was released publicly with open weights, enabling distillation by other labs (Source: DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning). Dense-model distillations shipped in 1.5B, 7B, 8B, 14B, 32B, and 70B sizes, with the distilled 32B model competitive with closed frontier models on reasoning (Source: DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning). Distillations into Qwen2.5 showed efficiency gains the Epoch AI account called "enormous" — several-fold less compute for GPQA and multiple orders of magnitude less for MATH (Source: epochai.substack.com). The model was released with roughly 4B tokens of distillation data, a relatively small amount but sufficient to meaningfully improve post-training (Source: epochai.substack.com). Anthropic accused DeepSeek of distilling from Claude's outputs (Source: epochai.substack.com).
The R1-to-small-dense distillations serve as a reference demonstration of reasoning distillability (see Distillation).
Reception and competitive context
DeepSeek-R1 caught up to OpenAI's o1 within months using less training compute, a case cited in discussions of the fast-follow problem. One account notes that if software efficiency improves on the order of 10× per year, the speed of the catch-up is less surprising (Source: The Least Understood Driver of AI Progress; see AI Software Progress). The open release prompted other Chinese labs to follow suit, including Baidu abandoning a closed-model commitment (see Open-Source AI / Open-Weight Models).
Related models
- DeepSeek-V3 — the base model R1 was built on.
- DeepSeek V4 Pro / V4 Flash — DeepSeek's later flagship generation.
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning — the model's technical paper.
- State of AI Report 2025 — covers R1 in the year's competitive landscape.
Relationships
- instance-of: Frontier Models
- depends-on: DeepSeek-V3 — base model
- supports: Fast-Follow Problem — cited as the reference fast-follow case
- related: Distillation, Open-Source AI / Open-Weight Models, AI Software Progress, US-China AI Competition: Different Races, Different Metrics