VerdictPal
Join

Models / DeepSeek

DeepSeek R1

DeepSeek R1 · Released 2025-01-20

DeepSeek's January 2025 reasoning model. Open weights, chain-of-thought style. MATH 79.8%, strong AIME scores with extended thinking.

Self-hosted reasoning route before V4 shipped. Still relevant for reproducible CoT research and local inference stacks.

#39 of 51 on AA Index · current snapshot
20 AA Index · 17 benchmark rows · 4 sourcesPosition is benchmark-specific — not a cross-family or cross-source ranking.
Composite55
Context128K
Input / 1M$0.55
Output / 1M$2.2
Knowledge cutoffopen
Output speed0 t/s
TTFT (default API)0.00s
Statuslightweight
DeepSeek
KnowledgeReasoningMathCodingAgenticLong contextTool use
Knowledge
87
Reasoning
81
Math
88
Coding
77
Agentic
37
Long context
55
Tool use
72

71average across 7 tested families

Benchmark placements

Where DeepSeek R1 places on each public benchmark source that publishes a row. Rank counts every model with a latest row in the same test — not a universal quality score.

BenchmarkFamilyRankScoreSourceDate
LiveCodeBenchCoding#6/ 1377Artificial Analysis2026-07-21
AIMEMath#7/ 1988DeepSeek R1 model card2025-01-20
MMLU-ProKnowledge#7/ 2185Artificial Analysis2026-07-21
LiveBenchReasoning#9/ 2164LiveBench leaderboard2026-04-15
MMLUKnowledge#14/ 2287DeepSeek R1 model card2025-01-20
MATHMath#16/ 2080DeepSeek R1 model card2025-01-20
BFCLTool use#18/ 2072Berkeley Function Calling Leaderboard V42026-04-15
τ³-Bench BankingAgentic#18/ 6437Artificial Analysis2026-07-21
GPQA DiamondReasoning#46/ 6981Artificial Analysis2026-07-21
SciCodeCoding#50/ 6540Artificial Analysis2026-07-21
Humanity's Last ExamReasoning#51/ 6515Artificial Analysis2026-07-21
AA-LCRLong context#53/ 6455Artificial Analysis2026-07-21
Artificial Analysis Intelligence IndexReasoning#55/ 6720Artificial Analysis2026-07-21
IFBenchReasoning#55/ 5740Artificial Analysis2026-07-21
AA output speedPerformance#61/ 69Artificial Analysis2026-07-21
AA time to first tokenPerformance#61/ 69Artificial Analysis2026-07-21
Terminal-BenchAgentic#62/ 6916Artificial Analysis2026-07-21
Family context

The three highest-scoring carded models in each capability family. Where DeepSeek R1 shows up, it's highlighted.

KnowledgeDeepSeek R1 · 87
  1. 1
    GPT 5.5
    91
  2. 2
    Claude Opus 4.8
    91
  3. 3
    Claude Sonnet 4.6
    91
ReasoningDeepSeek R1 · 81
  1. 1
    Claude Mythos Preview
    95
  2. 2
    GPT-5.6 Sol
    94
  3. 3
    Kimi K3
    94
MathDeepSeek R1 · 88
  1. 1
    OpenAI o3
    99
  2. 2
    OpenAI o1
    97
  3. 3
    Gemini 3 Pro
    96
CodingDeepSeek R1 · 77
  1. 1
    GPT 5.5
    96
  2. 2
    Claude Opus 4.8
    96
  3. 3
    Claude Opus 4.6
    96
AgenticDeepSeek R1 · 37
  1. 1
    GPT 5.5
    100
  2. 2
    Claude Opus 4.8
    100
  3. 3
    Claude Fable 5
    100
Long contextDeepSeek R1 · 55
  1. 1
    Kimi K3
    75
  2. 2
    GPT-5.1
    75
  3. 3
    GPT-5.6 Sol
    74
Tool useDeepSeek R1 · 72
  1. 1
    Claude Sonnet 4.6
    89
  2. 2
    GPT 5.5
    87
  3. 3
    Claude Opus 4.8
    87
Newest receipts

Benchmark rows added to the public ledger for DeepSeek R1 in the last 120 days. Older rows live in the full table below.

14 recent
BenchmarkFamilyScoreSourceDays ago
AA-LCRLong context54.67%Artificial Analysis2
AA output speedPerformance0 t/sArtificial Analysis2
AA time to first tokenPerformance0.00sArtificial Analysis2
Artificial Analysis Intelligence IndexReasoning20.1%Artificial Analysis2
GPQA DiamondReasoning81.3%Artificial Analysis2
Humanity's Last ExamReasoning14.9%Artificial Analysis2
IFBenchReasoning39.59%Artificial Analysis2
LiveCodeBenchCoding77%Artificial Analysis2
MMLU-ProKnowledge84.9%Artificial Analysis2
SciCodeCoding40.3%Artificial Analysis2
τ³-Bench BankingAgentic36.55%Artificial Analysis2
Terminal-BenchAgentic15.91%Artificial Analysis2
BFCLTool use72.4%Berkeley Function Calling Leaderboard V499
LiveBenchReasoning64.1%LiveBench leaderboard99
Family coverage

A high composite that hides a weak family is a trap. These bars surface the families where this model hasn't been publicly tested, and where it leads.

Knowledge87
Reasoning81
Math88
Coding77
Agentic37
Long context55
Tool use72
Price vs. performance
0255075100$0.10$0.30$1$3$10$30input USD / 1M tokens · log scale →← intelligence

Hover or tab any dot for name, score, and input price.

AnthropicOpenAIMistralAlibabaDeepSeekGoogleMoonshotMiniMaxxAIMetaZhipuXiaomiMeituanCohere

Full benchmark ledger

Every catalog benchmark for DeepSeek R1. Scores link to the original source; gaps mean no public row exists yet.

17 sourced rows

17 of 32 catalog benchmarks have a sourced row for DeepSeek R1.

Knowledge

Reasoning

Math

Coding

Agentic

Long context

Tool use

Performance

Sources