DeepSeek V4 Flash 0420 (Reasoning, High Effort)
Context 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.
| # | Provider | Platform | Raw input $/1M | Raw output $/1M | Adjusted $/task |
|---|---|---|---|---|---|
| 1 | OpenInference | OpenRouter | $0.050 | $0.140 | |
| 2 | DeepInfra | OpenRouter | $0.090 | $0.180 | |
| 3 | Venice | OpenRouter | $0.097 | $0.193 | |
| 4 | DigitalOcean | OpenRouter | $0.098 | $0.196 | |
| 5 | SiliconFlow | OpenRouter | $0.130 | $0.280 |
Composite
3 of 7 inputs · 1 from the model family6 radar axes: DesignArena's two boards share one54.4
dominance-adjusted from 55.8: a better-measured model that is at least as good on each of these inputs ranks above it
AA Coding 52.0Coding Agent v1.4 —AA Intelligence 24.8AA Agentic —Epoch ECI 146.1Software ECI —DesignArena —/—
Radar: percentile among all models measured on each input; a gap means not measured.
Benchmark sheet
22 of 140 registered benchmark versions · bars show the percentile among all models measured on each benchmark.
- Epoch ECI · attached
Agentic
AA-Briefcase561,052 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 v2541,083 Elo
GDPval-AA v2 v2 ↗ · Published board — Tests professional knowledge-work deliverables across occupations using AA's Stirrup harness.
Terminal-Bench Hard (AA)8638.6%
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)5656.9%
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)583.0%
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)7375.1%
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
SciCode (AA subproblems) v1.0.12940.2%
SciCode (AA subproblems) v1.0.1 ↗ · Published board — Tests scientific Python programming with scientist-annotated background information.
AA Coding Index5852.0
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 task85$0.0036
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 task95$0.0085
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)9173.5%
IFBench (AA single-turn) published 2026-09-10 ↗ · Published board — Tests precise single-turn instructions with deterministic rule checks.
LisanBench word chains, v0.2.0 (Lisan al Gaib)752,789
LisanBench word chains, v0.2.0 (Lisan al Gaib) v0.2.0 ↗ · Published board — A model builds the longest chain of English words it can, each differing from the last by one letter, with no repeats and only dictionary words, from 50 starting words; any broken rule ends the chain.
Knowledge
Humanity's Last Exam (AA text-only)8330.3%
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 Index61-23.1
AA-Omniscience Index published 2026-09-10 ↗ · Published board — Tests factual reliability while rewarding correct answers and penalizing hallucinations.
Long-context
GDP.pdf (AA)4610.4%
GDP.pdf (AA) published 2026-09-10 ↗ · Published board — Tests professional reasoning over long PDFs with AA document preparation and grading.
AA-LCR v1.17172.0%
AA-LCR v1.1 v1.1 ↗ · Published board — Tests reasoning across multiple long documents with corrected answer keys and grading.
MLCR-AA246.7%
MLCR-AA published 2026-09-10 ↗ · Published board — Tests medical-record synthesis and reasoning across long, fragmented case documents.
Reasoning
AA Intelligence Index8024.8
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)753.4%
CritPt (AA) published 2026-09-10 ↗ · Published board — Tests research-level physics reasoning with Python, symbolic and numerical answers.
GPQA Diamond (AA)8286.7%
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)8086.6%
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 v1.0.65528.5%
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)9595.6%
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) v1.0.16326.2%
τ³-Banking (AA) v1.0.1 ↗ · Published board — Tests banking support agents that retrieve policies and change account state through tools.
Missing coverage · 121 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)
| Variant | AA Coding | AA Intelligence |
|---|---|---|
| DeepSeek V4 Flash 0420 (Reasoning, Max Effort) | 56.2 | 24.6 |
| DeepSeek V4 Flash 0420 (Reasoning, High Effort) | 52.0 | 24.8 |
| DeepSeek V4 Flash 0420 (Non-reasoning) | — | 18.9 |
Token offers by platform · 14 offers (Adjusted $/task)
Click any underlined price to see how it is estimated and where each input comes from. How we calculate adjusted cost.
14 offers within the active global filters; “—” means the catalog is active but no public token price is available.
OpenRouter (11)
| OpenInference | globalopen-inference/fp8 | $0.050 raw in $/1M | $0.140 raw out $/1M | |
| DeepInfra | globaldeepinfra/fp8 | $0.090 raw in $/1M | $0.180 raw out $/1M | |
| Venice | globalvenice | $0.097 raw in $/1M | $0.193 raw out $/1M | |
| DigitalOcean | globaldigitalocean | $0.098 raw in $/1M | $0.196 raw out $/1M | |
| SiliconFlow | globalsiliconflow/fp8 | $0.130 raw in $/1M | $0.280 raw out $/1M | |
| Novita | globalnovita/fp8 | $0.140 raw in $/1M | $0.280 raw out $/1M | |
| NextBit | globalnextbit/fp8EU | $0.150 raw in $/1M | $0.350 raw out $/1M | |
| Parasail | globalparasail/fp8 | $0.140 raw in $/1M | $0.280 raw out $/1M | |
| Azure | globalazure/us | $0.210 raw in $/1M | $0.560 raw out $/1M | |
| Phala | globalphalaTEE | $0.200 raw in $/1M | $0.400 raw out $/1M | |
| Mancer 2 | globalmancer/fp8 | $0.190 raw in $/1M | $0.500 raw out $/1M |
Azure AI Foundry (3)
| Azure AI Foundry | usfireworks | $0.150 raw in $/1M | $0.310 raw out $/1M | |
| Azure AI Foundry | global | $0.190 raw in $/1M | $0.510 raw out $/1M | |
| Azure AI Foundry | euEU | $0.210 raw in $/1M | $0.560 raw out $/1M |