AI Model Timeline

Tracking the accelerating release frequency of frontier AI models.

DeepSeek-R1

DeepSeek·

LLMsreasoningcloud + localFrontier

Overview

Reasoning model capable of self-verification.

Capabilities and innovations

Chain of thoughtSelf-verificationRL trainingPure RL ReasoningSelf-verificationEmergent CoT Behavior

Benchmarks

BenchmarkScoreSource
GPQA Diamond71.5%unsourced
Humanity’s Last Exam (no tools)18.4%unsourced
SWE-bench Verified49.2%unsourced
MMLU90.8%unsourced
MMLU-Pro83.18%unsourced
  • SWE-bench Pro: benchmark did not exist at release
  • Terminal-Bench 2.x: benchmark did not exist at release
  • MMMU-Pro: benchmark did not exist at release

Architecture and hardware

Parameters
671B total, 37B active per token (MoE)
Estimated VRAM at Q4
~386 GB, Frontier class

Links

More from DeepSeek

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