← All models

DeepSeek V3.2 (Reasoning)

open weightsdeprecated by benchmark source
DeepSeek · released 2025-12-01 · 19 offers

Context 128K tokens

Top 5 cheapest providers (Adjusted $/task)

The same list price can give a different adjusted $/task (caching, token efficiency) — click a price for its inputs.

Within the active global provider, residency and confidentiality filters.

#ProviderAdjusted $/task
1DeepInfra
2Venice
3SiliconFlow
4Novita
5DigitalOcean

Composite

4 of 7 inputs · 2 from the model family6 radar axes: DesignArena's two boards share one

48.6

AA CodingCoding Agent v1.4AA IntelligenceAA AgenticEpoch ECISoftware ECIDesignArenaAA Coding: percentile 50AA Intelligence: percentile 73Epoch ECI: percentile 41Software ECI: percentile 26

AA Coding 44.2Coding Agent v1.4 AA Intelligence 21.5AA Agentic Epoch ECI 146.2Software ECI 145.7DesignArena —/—

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

Benchmark sheet

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

Composite attachments (used in the score, not counted as exact benchmarks):
  • Epoch ECI · attached
  • Software ECI · attached
Compare this model →

Agentic

  • APEX-Agents-AA3114.5%

    APEX-Agents-AA published 2026-09-10 · Published board — Tests professional-service tasks that require agents to produce locally graded deliverables.

  • GDPval-AA v237810 Elo

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

  • Terminal-Bench Hard (AA)8235.6%

    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)4746.8%

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

  • τ²-Bench Airline (OpenRouter run)5872.1%

    τ²-Bench Airline (OpenRouter run) published 2026-09-15 · Published board — Multi-turn service agents making tool calls under strict policy constraints. (OpenRouter's own reproducible run, as published on openrouter.ai/benchmarks.)

Coding

  • AA Coding Index5044.2

    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.

Efficiency

Instruction-following

Knowledge

Long-context

  • AA-LCR v1.17473.3%

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

Math

  • AIME 2025 (AA) v20259492.0%

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

Reasoning

Science

Tool-use

Missing coverage · 127 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.

Variants / reasoning settings

Artificial Analysis snapshot 2026-09-19 · Data: Artificial Analysis · Data: Epoch AI (CC BY)

VariantAA CodingAA Intelligence
DeepSeek V3.2 (Reasoning)44.221.5
DeepSeek V3.2 (Non-reasoning)16.0
Token offers by platform · 13 offers (Adjusted $/task)

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

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

OpenRouter (9)

DeepInfra
Venice
SiliconFlow
Novita
DigitalOcean
Google
Phala
Mara
SambaNova

Chutes (1)

Chutes

Google Vertex AI (1)

Google Vertex AI

Azure AI Foundry (1)

Azure AI Foundry

AWS Bedrock (1)

AWS Bedrock
DeepSeek V3.2 (Reasoning) — benchmarks & cost | Benchmark Heaven