AI Model Timeline

Tracking the accelerating release frequency of frontier AI models.

DeepSeek-R1

DeepSeek·

LLMsopen-weightFrontier

Overview

First open reasoning model using reinforcement learning. Matched OpenAI o1 on math and coding reasoning tasks without supervised fine-tuning for chain-of-thought.

Capabilities and innovations

671B total / 37B active parameters (MoE)128K context windowChain-of-thought reasoningDistilled variants (1.5B to 70B)Pure RL-based reasoning (no SFT for CoT)Group Relative Policy Optimization (GRPO)Self-verification via reasoning chainsKnowledge distillation to smaller models

Benchmarks

BenchmarkScoreSource
GPQA Diamond71.5%unsourced
Humanity’s Last Exam (no tools)8.5%unsourced
SWE-bench Verified49.2%unsourced
MMLU90.8%unsourced

Architecture and hardware

Parameters
671B total, 37B active per token (MoE)
Estimated VRAM at Q4
~386 GB, Frontier class
Quantization formats
GGUF, GPTQ, AWQ
Recommended runtime
Ollama
License
MIT

Links

More from DeepSeek

Data curated by AI Model Timeline. See the methodology for admission criteria, benchmark eras and source priority.