Benchmarks
More
OverviewBenchmaxxingCompareChartsCost vs CapabilityProviders per ModelProvider explorerGatewaysEU & SovereignJev-class modelsAbout
← All models

DeepSeek R1 (Jan '25)

open weightsdeprecated by benchmark source
DeepSeek · released 2025-01-20 · 1 offers

Context 128K tokens

Top 1 cheapest providers (Adjusted $/task)

Within the active global provider, residency and confidentiality filters.

#ProviderAdjusted $/task
1Novita

Composite

2 of 7 inputs6 radar axes: DesignArena's two boards share one

22.3

dominance-adjusted from 24.4: a better-measured model that is at least as good on each of these inputs ranks above it

AA CodingCoding Agent v1.4AA IntelligenceAA AgenticEpoch ECISoftware ECIDesignArenaAA Coding: percentile 30AA Intelligence: percentile 50AA Agentic: percentile 15

AA Coding 24.6Coding Agent v1.4 —AA Intelligence 11.4AA Agentic 1.1Epoch ECI —Software ECI —DesignArena —/—

Radar: percentile among all models measured on each input; a gap means not measured.

Benchmark sheet

24 of 140 registered benchmark versions · bars show the percentile among all models measured on each benchmark.

Compare this model →

Agentic

  • AA-Briefcase7150 Elo

    AA-Briefcase published 2026-09-10 ↗ · Published board — Tests multi-week professional knowledge-work projects with linked tasks and large source collections.

  • GDPval-AA v219479 Elo

    GDPval-AA v2 v2 ↗ · Published board — Tests professional knowledge-work deliverables across occupations using AA's Stirrup harness.

  • Terminal-Bench Hard (AA)346.1%

    Terminal-Bench Hard (AA) pinned revision 74221fb ↗ · Published board — Tests a pinned 44-task hard subset of terminal-based work using Terminus 2.

  • Terminal-Bench v2.1 (AA)2519.1%

    Terminal-Bench v2.1 (AA) v2.1 ↗ · Published board — Tests terminal-based work on the 89-task verified refresh using Terminus 2.

  • Terminal-Bench v4.0 (AA)180.0%

    Terminal-Bench v4.0 (AA) v4.0 ↗ · Published board — Tests terminal-based work on the 66-task release using mini-SWE-agent v2.4.6.

  • AA Agentic Index151.10

    AA Agentic Index published 2026-09-18 ↗ · Published board — Artificial Analysis publishes one Agentic Index per model, measured on its primary configuration and relayed by OpenRouter's Benchmarks API; the value is attached at family scope on the deterministic representative. Artificial Analysis publishes this board without a version number; we keep the date each result was retained.

Coding

  • SciCode (AA subproblems) v1.0.12238.3%

    SciCode (AA subproblems) v1.0.1 ↗ · Published board — Tests scientific Python programming with scientist-annotated background information.

  • AA Coding Index3024.6

    AA Coding Index published 2026-09-19 ↗ · Published board — Artificial Analysis publishes this board without a version number; we keep the date each result was retained.

Instruction-following

Knowledge

Long-context

  • GDP.pdf (AA)212.4%

    GDP.pdf (AA) published 2026-09-10 ↗ · Published board — Tests professional reasoning over long PDFs with AA document preparation and grading.

  • AA-LCR v1.15357.7%

    AA-LCR v1.1 v1.1 ↗ · Published board — Tests reasoning across multiple long documents with corrected answer keys and grading.

Math

  • AIME 2025 (AA) v20256268.0%

    AIME 2025 (AA) v2025 ↗ · Published board — Advanced mathematical problem solving on AIME I and II 2025.

Reasoning

Science

Tool-use

  • AutomationBench-AA v1.0.650.2%

    AutomationBench-AA v1.0.6 ↗ · Published board — Tests multi-app SaaS workflows through REST tools on a held-out AutomationBench split.

  • τ²-Bench Telecom (AA)911.4%

    τ²-Bench Telecom (AA) published 2026-09-10 ↗ · Published board — Tests dual-control telecom agents that coordinate tool use with a simulated user.

  • τ³-Banking (AA) v1.0.1186.4%

    τ³-Banking (AA) v1.0.1 ↗ · Published board — Tests banking support agents that retrieve policies and change account state through tools.

Uncensored

  • UGI Willingness362.80

    UGI Willingness published 2026-09-10 ↗ · Published board — A private-question evaluation of how far a model follows challenging instructions before refusing or deviating.

  • UGI8851.0

    UGI published 2026-09-10 ↗ · Published board — A private-question suite combining sensitive-topic knowledge with willingness to follow controversial instructions.

Writing

  • EQ-Bench Creative Writing v3831,500 Elo

    EQ-Bench Creative Writing v3 v3 ↗ · Published board — A LLM-judged creative writing benchmark with vocabulary and GPT-slop controls.

  • EQ-Bench Longform Creative Writing v1.116859.5

    EQ-Bench Longform Creative Writing v1.11 ↗ · Published board — LLM-judged benchmark in which models plan and write a short story/novella over 8x 1000-word turns, scored 0-100 across 14 rubric dimensions.

  • UGI Writing9451.8

    UGI Writing published 2026-09-10 ↗ · Published board — A maintainer-owned writing evaluation considering intelligence, style, repetition and length adherence, informed by human preferences.

Unusual results

4 threshold-crossing signals flagged · 25 eligible benchmark families

How flags are calculated

Heuristic screen, not statistical significance: benchmark families are correlated and source uncertainty is unknown. Peer evidence needs ≥ 20 independently measured matched configurations from ≥ 10 distinct model families. A flag needs a directed population z-score of magnitude ≥ 1.5 and a gap of ≥ 1.5 from the leave-one-benchmark-family-out mean z in the same direction, over ≥ 5 other benchmark families.

Missing coverage · 119 benchmark versions

No result does not mean a zero, or that the model was never tested. Collection failures and disputed versions retain their distinct status.

Token offers by platform · 1 offers (Adjusted $/task)

Click any underlined price to see how it is estimated and where each input comes from. How we calculate adjusted cost.

1 offers within the active global filters; “—” means the catalog is active but no public token price is available.

OpenRouter (1)

Novita
DeepSeek R1 (Jan '25) — benchmarks & cost | Benchmark Heaven