← All models

DeepSeek V4 Flash 0731 (Reasoning, Max Effort)

open weightsdeprecated by benchmark source
DeepSeek · released 2026-07-31 · 33 offers

Output 241 tokens/sFirst token 0.9 sContext 1M 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
1Relace
2Inceptron
3DeepInfra
4Inceptron
5Sail Research

Composite

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

75.0

AA CodingCoding Agent v1.4AA IntelligenceAA AgenticEpoch ECISoftware ECIDesignArenaAA Coding: percentile 79Coding Agent v1.4: percentile 33AA Intelligence: percentile 91AA Agentic: percentile 80Epoch ECI: percentile 64Software ECI: percentile 44

AA Coding 69.1Coding Agent v1.4 49.8AA Intelligence 34.5AA Agentic 41.7Epoch ECI 154.5Software ECI 150.0DesignArena —/—

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

Benchmark sheet

30 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

  • AA-Briefcase711,259 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 v2851,468 Elo

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

  • Terminal-Bench v2.1 (AA)7978.7%

    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)7212.1%

    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.

  • τ²-Bench Airline (OpenRouter run)6072.8%

    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.)

  • AA Agentic Index8041.7

    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

Efficiency

Knowledge

Long-context

  • GDP.pdf (AA)4911.0%

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

  • AA-LCR v1.18879.7%

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

  • MLCR-AA4813.3%

    MLCR-AA published 2026-09-10 · Published board — Tests medical-record synthesis and reasoning across long, fragmented case documents.

Math

  • FrontierMath Tiers 1–3 v2 (Epoch AI)2757.5%

    FrontierMath Tiers 1–3 v2 (Epoch AI) v2 · Published board — Unpublished, expert-written mathematics problems from undergraduate to research level with automatically checkable answers, run by Epoch AI on its private v2 set.

  • FrontierMath Tier 4 v2 (Epoch AI)1724.4%

    FrontierMath Tier 4 v2 (Epoch AI) v2 · Published board — The hardest, research-level tier of Epoch AI's unpublished FrontierMath problems, run by Epoch AI on its private v2 set.

Reasoning

  • Chess Puzzles (Epoch AI)6433.0%

    Chess Puzzles (Epoch AI) published 2026-09-18 · Published board — Best-move selection on 100 novel chess positions generated programmatically by Epoch AI, each with a single Stockfish-verified best move; probes spatial reasoning and planning.

  • Mystery Game Puzzles (Epoch AI)6434.0%

    Mystery Game Puzzles (Epoch AI) published 2026-09-18 · Published board — Best-move selection on 100 mid-game positions of a well-known game whose identity Epoch deliberately keeps undisclosed, generated programmatically like Chess Puzzles.

  • AA Intelligence Index9134.5

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

Science

Tool-use

  • AutomationBench-AA v1.0.67854.0%

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

  • τ³-Banking (AA) v1.0.18439.4%

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

Writing

  • EQ-Bench Creative Writing v3741,438 Elo

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

  • Judgemark v43330.7

    Judgemark v4 v4 · Published board — Meta-evaluation that rates LLM judges on how discriminatively they score fixed creative-writing samples.

  • EQ-Bench Longform Creative Writing v1.117661.2

    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.

Missing coverage · 113 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 · 27 offers (Adjusted $/task)

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

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

OpenRouter (21)

OpenInferencefreeFree route: rate- and quota-limited, availability may change — not used as a paid pricenot a paid price
Relace
Inceptron
DeepInfra
Sail Research
Reka
BaseTen
Fireworks
Wafer
Together
Makora
DigitalOcean
Venice
CoreWeave
Morph
Parasail
Novita
SiliconFlow
NextBit
Phala
Mancer 2

Inceptron (1)

Inceptron

TensorX (1)

TensorX

Nebius (1)

Nebius

Chutes (1)

Chutes

Scaleway (1)

Scaleway

Azure AI Foundry (1)

Azure AI Foundry
DeepSeek V4 Flash 0731 (Reasoning, Max Effort) — benchmarks & cost | Benchmark Heaven