DeepSeek

DeepSeek R1

A mixture-of-experts reasoning model released with permissive weights. R1 made high-end chain-of-thought style performance more accessible to self-hosted teams.

reasoningopen-weightsmathcoding

Model record

DeepSeek R1 model overview

DeepSeek R1 is a open weights model from DeepSeek. It was released on January 20, 2025. Its strongest case is permissive open-weight release, while buyers should account for full model has demanding infrastructure needs.

DeepSeek R1 benchmark snapshot

EvaluationReported scoreWhat it probes
MMLU-Pro84Broad knowledge and multi-step reasoning
GPQA Diamond71.5Graduate-level science reasoning
SWE-bench Verified49.2Verified real-repository issue resolution
LiveCodeBench65.9Contamination-aware competitive programming
SWE-Bench ProNot reportedLonger, harder professional software tasks
Artificial Analysis Intelligence IndexNot reportedComposite third-party capability index; version matters

Scores are percentages reported by model creators or benchmark maintainers under varying settings. A blank is preferable to an inferred result. See our methodology.

DeepSeek R1 strengths

  • Permissive open-weight release
  • Strong math and reasoning
  • Multiple distilled variants

DeepSeek R1 limitations

  • Full model has demanding infrastructure needs
  • Long reasoning traces add latency
Editorial take: Benchmark rank should narrow a shortlist, not close a purchase. Run a private evaluation with representative prompts, failure cases, latency targets, and total token costs.

Compare DeepSeek R1

Source record

Specifications and scores are linked to the best source located during review. Provider-reported results are not presented as third-party lab reproductions.

Read DeepSeek R1 repository