Skip to main content

Model profile

DeepSeek-R1

DeepSeekEstablishedReleased Jan 20, 2025
Data verified
Overall Score
51.67Public #103 of 200Verified #56 of 99
Arena Elo
1398
Eligible category ranks
0of 8
Price (1M tokens)
$0.55 in / $2.19 out
API pricing
Speed
Not listed
Context
128K

Evidence coverage

11 of 321 tracked benchmarks are published. 0 are verified and 11 provisional. 5 of 8 categories are measured.

Updated July 20, 2026Methodology
Published / tracked
11 / 321
Verified
0
Provisional
11
Categories with evidence
5 / 8

Evidence by category

  • Agentic1 benchmark
    Reported
  • Coding1 benchmark
    Reported
  • Reasoning2 benchmarks
    Reported
  • Knowledge6 benchmarks
    Reported
  • Math0 benchmarks
    Not measured
  • Multilingual0 benchmarks
    Not measured
  • Multimodal0 benchmarks
    Not measured
  • Inst. Following1 benchmark
    Reported
Open WeightSelf-hostReasoning
Confidence:
Low
base

DeepSeek-R1 ranks #103 out of 200 models on the public leaderboard with an overall score of 51.67/100. It also ranks #56 out of 99 on the verified leaderboard. While not a frontier model, it offers specific advantages depending on the use case.

DeepSeek-R1 is a open weight model with a 128K token context window. It uses explicit chain-of-thought reasoning, which typically improves performance on math and complex reasoning tasks at the cost of higher latency and token usage.

This profile currently has 11 of 321 tracked benchmarks. BenchLM only exposes non-generated benchmark rows publicly, so missing categories stay blank until a sourced evaluation is available.

Peer position

Exact provisional scores and ranks for the closest listed peers. A score can appear before a model clears the evidence threshold for a rank, so equal scores can have different rank states.

Range 51.2552.15

  1. Qwen2.5-72B
    Alibaba
    #10152.15
    Qwen2.5-72B is #101 with a score of 52.15.
    Compare
  2. Llama 3.1 405B
    Meta
    #10251.71
    Llama 3.1 405B is #102 with a score of 51.71.
    Compare
  3. DeepSeek-R1Current model
    DeepSeek
    #10351.67
    DeepSeek-R1 is #103 with a score of 51.67.
  4. Qwen3.6-35B-A3B
    Alibaba
    #10451.47
    Qwen3.6-35B-A3B is #104 with a score of 51.47.
    Compare
  5. Mercury 2
    Inception
    #10551.28
    Mercury 2 is #105 with a score of 51.28.
    Compare
  6. GLM-4.7-Flash
    Z.AI
    #10651.25
    GLM-4.7-Flash is #106 with a score of 51.25.
    Compare
  7. Grok 4.1 Fast
    xAI
    #10751.25
    Grok 4.1 Fast is #107 with a score of 51.25.
    Compare

Category percentile

More

Relative position among models eligible for each sourced category. A higher percentile means a stronger position within that category's ranked cohort; 100 is highest.

No eligible category percentile is available from the published evidence yet.

Category evidence

Scores and ranks appear only where this model has published benchmark evidence. Categories without displayable source records remain not measured.

Category scores, ranks, weighting, benchmark coverage, and evidence status
CategoryScore
AgenticRank Not rankedWeight 22%1 benchmarkReported44.6
CodingRank Not rankedWeight 20%1 benchmarkReported27.5
ReasoningRank Not rankedWeight 17%2 benchmarksReported40.1
KnowledgeRank Not rankedWeight 12%6 benchmarksReported42.7
MathWeight 5%0 benchmarksNot measuredNot measured
MultilingualWeight 7%0 benchmarksNot measuredNot measured
MultimodalWeight 12%0 benchmarksNot measuredNot measured
Inst. FollowingRank Not rankedWeight 5%1 benchmarkReported83.3

Self-host vs API cost

Estimates at 50,000 req/day · 1000 tokens/req average.

DeepSeek-R1
API / mo$2,055
Self-host / mo$18,221
Break-even583M/day
Model the full break-even

Chatbot Arena performance

Scroll horizontally to inspect confidence intervals and vote counts.

Chatbot Arena Elo, confidence interval, and vote count by evaluation view
ViewEloConfidence intervalVotes
Text Overall1398±4.918,524
Coding1445±11.82,317
Math1412±14.01,606
Instruction Following1397±7.56,426
Creative Writing1374±10.43,289
Multi-turn1410±11.92,418
Hard Prompts1419±9.04,116
Hard Prompts (English)1433±11.22,656
Longer Query1399±12.02,303

Benchmark Details

Rows below have a displayable published verification record. Each source link and provenance note remains in the page HTML while its category is closed. Source-unverified manual rows and generated rows stay hidden.

Agentic1 benchmark
τ²-bench resultsReported

τ²-Bench Tool-Agent-User Evaluation

36.5%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
Coding1 benchmark
AA-SciCodeReported

Artificial Analysis SciCode

40.3%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
Reasoning2 benchmarks
AA-LCRReported

Artificial Analysis Long Context Reasoning

54.7%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
CritPtReported

Critical Physics Tasks

1.4%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
Knowledge6 benchmarks
Artificial Analysis Intelligence IndexReported
20.1%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
AA-GPQA DiamondReported

Artificial Analysis GPQA Diamond

81.3%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
AA-HLEReported

Artificial Analysis Humanity's Last Exam

14.9%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
AA-Omniscience IndexReported

Artificial Analysis Omniscience Index

-27.1%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
AA-Omniscience AccuracyReported

Artificial Analysis Omniscience Accuracy

31.0%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
AA-Omniscience Hallucination RateReported

Artificial Analysis Omniscience Hallucination Rate

84.0%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
Inst. Following1 benchmark
AA-IFBenchReported

Artificial Analysis IFBench

39.6%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.

Frequently Asked Questions

How does DeepSeek-R1 perform overall in AI benchmarks?

DeepSeek-R1 has 11 published benchmark scores on BenchLM, but it does not yet have enough non-generated coverage to receive a global overall rank.

Is DeepSeek-R1 good for knowledge and understanding?

DeepSeek-R1 has visible benchmark coverage in knowledge and understanding, but BenchLM does not currently assign it a global category rank there.

Is DeepSeek-R1 good for coding and programming?

DeepSeek-R1 has visible benchmark coverage in coding and programming, but BenchLM does not currently assign it a global category rank there.

Is DeepSeek-R1 good for reasoning and logic?

DeepSeek-R1 has visible benchmark coverage in reasoning and logic, but BenchLM does not currently assign it a global category rank there.

Is DeepSeek-R1 good for agentic tool use and computer tasks?

DeepSeek-R1 has visible benchmark coverage in agentic tool use and computer tasks, but BenchLM does not currently assign it a global category rank there.

Is DeepSeek-R1 good for instruction following?

DeepSeek-R1 has visible benchmark coverage in instruction following, but BenchLM does not currently assign it a global category rank there.

Is DeepSeek-R1 open source?

Yes, DeepSeek-R1 is an open weight model created by DeepSeek, meaning it can be downloaded and run locally or fine-tuned for specific use cases.

Does DeepSeek-R1 have full benchmark coverage on BenchLM?

Not yet. DeepSeek-R1 currently has 11 published benchmark scores out of the 321 benchmarks BenchLM tracks. BenchLM only exposes non-generated public benchmark rows, so missing categories stay blank until a sourced evaluation is available.

What is the context window size of DeepSeek-R1?

DeepSeek-R1 has a published context window of 128K, which determines how much text it can process in a single interaction.

Last updated: July 20, 2026 · Runtime metrics stay blank until BenchLM has a sourced snapshot.

Choose with this week’s evidence

Join 2,000+ readers for ranking moves, new releases, pricing changes, and the evidence behind them.

Free. One email per week.