DeepSeek V3 0324
Context 128K tokens
Top 2 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.
| # | Provider | Platform | Raw input $/1M | Raw output $/1M | Adjusted $/task |
|---|---|---|---|---|---|
| 1 | DeepInfra | OpenRouter | $0.240 | $0.900 | |
| 2 | SiliconFlow | OpenRouter | $0.250 | $1.00 |
Composite
2 of 7 inputs6 radar axes: DesignArena's two boards share one18.9
AA Coding 21.2Coding Agent v1.4 —AA Intelligence 9.7AA Agentic 0.8Epoch ECI —Software ECI —DesignArena —/—
Radar: percentile among all models measured on each input; a gap means not measured.
Benchmark sheet
28 of 140 registered benchmark versions · bars show the percentile among all models measured on each benchmark.
Agentic
AA-Briefcase392 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 v213275 Elo
GDPval-AA v2 v2 ↗ · Published board — Tests professional knowledge-work deliverables across occupations using AA's Stirrup harness.
Terminal-Bench Hard (AA)5215.2%
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)2113.9%
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.
τ²-Bench Airline (OpenRouter run)1343.0%
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 Index60.80
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) v1.0.12639.0%
SciCode (AA subproblems) v1.0.1 ↗ · Published board — Tests scientific Python programming with scientist-annotated background information.
AA Coding Index2421.2
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
GPQA Diamond (OpenRouter run) — measured cost per task91$0.002
GPQA Diamond (OpenRouter run) — measured cost per task published 2026-09-15 ↗ · Published board — Mean USD OpenRouter actually spent per task while running GPQA Diamond for this configuration.
τ²-Bench Airline (OpenRouter run) — measured cost per task56$0.042
τ²-Bench Airline (OpenRouter run) — measured cost per task published 2026-09-15 ↗ · Published board — Mean USD OpenRouter actually spent per task while running τ²-Bench Airline for this configuration.
Instruction-following
IFBench (AA single-turn)4041.0%
IFBench (AA single-turn) published 2026-09-10 ↗ · Published board — Tests precise single-turn instructions with deterministic rule checks.
Knowledge
Humanity's Last Exam (AA text-only)264.7%
Humanity's Last Exam (AA text-only) published 2026-09-10 ↗ · Published board — Tests expert-level knowledge on AA's text-only Humanity's Last Exam subset.
AA-Omniscience Index47-40.7
AA-Omniscience Index published 2026-09-10 ↗ · Published board — Tests factual reliability while rewarding correct answers and penalizing hallucinations.
UGI NatInt9247.3
UGI NatInt published 2026-09-10 ↗ · Published board — A private-question evaluation of general knowledge and reasoning across textbook, popular-culture and world-model topics.
Long-context
GDP.pdf (AA)171.6%
GDP.pdf (AA) published 2026-09-10 ↗ · Published board — Tests professional reasoning over long PDFs with AA document preparation and grading.
AA-LCR v1.13940.7%
AA-LCR v1.1 v1.1 ↗ · Published board — Tests reasoning across multiple long documents with corrected answer keys and grading.
Math
AIME 2025 (AA) v20254241.0%
AIME 2025 (AA) v2025 ↗ · Published board — Advanced mathematical problem solving on AIME I and II 2025.
Reasoning
AA Intelligence Index449.70
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
CritPt (AA)240.0%
CritPt (AA) published 2026-09-10 ↗ · Published board — Tests research-level physics reasoning with Python, symbolic and numerical answers.
GPQA Diamond (AA)4165.5%
GPQA Diamond (AA) published 2026-09-10 ↗ · Published board — Tests graduate-level biology, physics and chemistry knowledge on the Diamond subset.
GPQA Diamond (OpenRouter run)1557.7%
GPQA Diamond (OpenRouter run) published 2026-09-15 ↗ · Published board — Graduate-level science questions that resist retrieval and reward careful reasoning. (OpenRouter's own reproducible run, as published on openrouter.ai/benchmarks.)
Tool-use
AutomationBench-AA v1.0.660.3%
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)5147.1%
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) v1.0.184.7%
τ³-Banking (AA) v1.0.1 ↗ · Published board — Tests banking support agents that retrieve policies and change account state through tools.
Uncensored
UGI Willingness835.80
UGI Willingness published 2026-09-10 ↗ · Published board — A private-question evaluation of how far a model follows challenging instructions before refusing or deviating.
UGI9555.0
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 v3781,470 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 v1.117260.1
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 Writing9349.1
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 · 29 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.
- unusually strong UGI published 2026-09-10
Why
Observed: 54.97 pointsPeer mean 30.75703 · peer sd 13.08304 · n 74 · families 73Directed z 1.851 · baseline z -0.31 · gap 2.161 · profile n 2854.97 pointsmeasuredobserved 2026-09-10huggingface.co ↗Evidence
Axis: UGI · published 2026-09-10 · Published boardExact value:54.97pointsObserved: 2026-09-10T22:04:13Z · publication date: not recordedObservation id:public:37f214c3ebb987900ee4037d - unusually strong UGI NatInt published 2026-09-10
Why
Observed: 47.28 pointsPeer mean 26.4323 · peer sd 11.33206 · n 74 · families 73Directed z 1.84 · baseline z -0.31 · gap 2.15 · profile n 2847.28 pointsmeasuredobserved 2026-09-10huggingface.co ↗Evidence
Axis: UGI NatInt · published 2026-09-10 · Published boardExact value:47.28pointsObserved: 2026-09-10T22:04:13Z · publication date: not recordedObservation id:public:964672ed02037829cf1c5dc8 - unusually strong UGI Writing published 2026-09-10
Why
Observed: 49.07 pointsPeer mean 31.68366 · peer sd 10.68331 · n 71 · families 70Directed z 1.627 · baseline z -0.303 · gap 1.93 · profile n 2849.07 pointsmeasuredobserved 2026-09-10huggingface.co ↗Evidence
Axis: UGI Writing · published 2026-09-10 · Published boardExact value:49.07pointsObserved: 2026-09-10T22:04:13Z · publication date: not recordedObservation id:public:c47d7b4b2c4531681dc96d67 - unusually weak AA-Briefcase published 2026-09-10
Why
Observed: 91.96 EloPeer mean 916.66604 · peer sd 463.03709 · n 154 · families 108Directed z -1.781 · baseline z -0.181 · gap -1.6 · profile n 2891.96 Elomeasuredobserved 2026-09-10artificialanalysis.ai ↗Evidence
Axis: AA-Briefcase · published 2026-09-10 · Published boardExact value:91.96EloObserved: 2026-09-10T21:47:16.627Z · publication date: not recordedObservation id:aa:75e1c197-f239-4361-a9d6-66dccfead236:briefcaseBreakdown.overall.elo
Missing coverage · 115 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 · 2 offers (Adjusted $/task)
Click any underlined price to see how it is estimated and where each input comes from. How we calculate adjusted cost.
2 offers within the active global filters; “—” means the catalog is active but no public token price is available.
OpenRouter (2)
| SiliconFlow | globalsiliconflow/fp8 | $0.250 raw in $/1M | $1.00 raw out $/1M | |
| DeepInfra | globaldeepinfra/fp4 | $0.240 raw in $/1M | $0.900 raw out $/1M |