Back to the index
DeepSeek · DeepSeek
No. 27

DeepSeek-R1-0528

Iconic open reasoning model — strong math at low cost, now a generation behind.

ReasoningOpen weightsText
Field notes
Context window
164Ktokens
Max output
66Ktokens
Input price
$0.50/ 1M tokens
Output price
$2.15/ 1M tokens
Cached input
$0.14/ 1M tokens
Modalities
Text
Knowledge cutoff
Apr 2025
Released
May 2025
Parameters
671B
License
MIT
Approx. speed
Overview

What this model is

DeepSeek-R1-0528 is DeepSeek's open-weight reasoning flagship (671B MoE, 37B active, MIT), known for transparent long chain-of-thought and excellent math and competition performance at a fraction of closed-model cost. It remains a popular self-hosted reasoner, though 2026 flagships have surpassed it and its long reasoning traces make it slow. Best for math, logic, and reasoning-heavy tasks rather than long agentic coding.

Strengths

  • Elite math and competition reasoning
  • Transparent, fully open MIT-licensed weights
  • Strong on GPQA-Diamond and AIME-style problems
  • Distillable into smaller models for cheaper reasoning

Trade-offs

  • Slow and token-heavy due to long reasoning traces
  • Agentic-coding reliability below the frontier
  • Surpassed by newer 2026 reasoners
  • Text-only, verbose on simple queries

Best for

  • Hard math and scientific reasoning
  • Competitive programming and algorithm design
  • Reasoning research and distillation
  • Self-hosted reasoning workloads

Not ideal for

  • Low-latency interactive chat
  • Long autonomous agentic coding
Capabilities

Capability profile

Normalized 0–100 scores, comparable across the whole catalog.

Reasoning85Coding68Math92Writing74Knowledge82Speed45Agentic62Vision5Multilingual80Long Context74
Reasoning
85
Coding
68
Math
92
Writing
74
Knowledge
82
Speed
45
Agentic
62
Vision
5
Multilingual
80
Long Context
74
Benchmarks

How it scores

Public benchmark results, with independent third-party results where available. Bars normalize percentages to 100 and Elo ratings to a 1500 ceiling.

BenchmarkResult
Aider Polyglotindependent
CodingAider
71.6%
MATH
MathVendor-reported
97.3%
MMLU-Pro
KnowledgeVendor-reported
85%
GPQA Diamondindependent
ReasoningIndependent aggregators
81%
AIME 2025
MathVendor-reported
87.5%
LiveCodeBenchindependent
CodingLiveCodeBench
65.9%
SWE-bench Verifiedindependent
CodingSWE-bench
57.6%
LMArena Eloindependent
GeneralLMArena
1410Elo
Alternatives

Comparable models

Models in a roughly similar class — worth weighing against this one.