DeepSeek V4 Pro 0424 (Reasoning, Max Effort)
Output 95 tokens/sFirst token 1.1 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.
| # | Provider | Platform | Raw input $/1M | Raw output $/1M | Adjusted $/task |
|---|---|---|---|---|---|
| 1 | DigitalOcean | OpenRouter | $1.04 | $2.09 | |
| 2 | DeepInfra | OpenRouter | $1.30 | $2.60 | |
| 3 | SiliconFlow | OpenRouter | $1.50 | $3.13 | |
| 4 | Novita | OpenRouter | $1.60 | $3.20 | |
| 5 | Parasail | OpenRouter | $1.74 | $3.48 |
Composite
4 of 7 inputs · 2 from the model family6 radar axes: DesignArena's two boards share one63.1
AA Coding 59.4Coding Agent v1.4 —AA Intelligence 30.9AA Agentic 27.7Epoch ECI 149.1Software ECI 146.6DesignArena —/—
Radar: percentile among all models measured on each input; a gap means not measured.
Benchmark sheet
39 of 140 registered benchmark versions · bars show the percentile among all models measured on each benchmark.
- Epoch ECI · attached
- Software ECI · attached
Agentic
AA-AnalystAgent3418.8%
AA-AnalystAgent published 2026-09-10 ↗ · Published board — Tests analyst tasks using agentic Python execution across fourteen domains.
APEX-Agents-AA4824.3%
APEX-Agents-AA published 2026-09-10 ↗ · Published board — Tests professional-service tasks that require agents to produce locally graded deliverables.
AA-Briefcase47925 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 v2671,223 Elo
GDPval-AA v2 v2 ↗ · Published board — Tests professional knowledge-work deliverables across occupations using AA's Stirrup harness.
Harvey LAB-AA4584.4%
Harvey LAB-AA published 2026-09-10 ↗ · Published board — Tests legal-work deliverables across practice areas on Harvey's private task set. Artificial Analysis' run, graded by one LLM judge against task rubrics — not the same run or scale as Vals AI's HLAB row.
ITBench-AA6638.3%
ITBench-AA published 2026-09-10 ↗ · Published board — Tests root-cause diagnosis from offline Kubernetes incident snapshots.
Terminal-Bench Hard (AA)9346.2%
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)6364.0%
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)7814.6%
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.
ApprenticeBench API (NeoCognition)3121.0%
ApprenticeBench API (NeoCognition) published 2026-09-14 ↗ · Claude Code — An agent completes the same 100 sequential accounts-payable tasks in the Odoo ERP with diminishing mentoring, using dedicated application API calls instead of the screen interface.
Vals Index v2 (Vals AI)2042.9%
Vals Index v2 (Vals AI) v2 ↗ · Published board — GDP-weighted average of agentic model performance across finance, coding and legal tasks.
Finance Agent v2 (Vals Index v2)1744.1%
Finance Agent v2 (Vals Index v2) v2 ↗ · Published board — Multi-step financial reasoning tasks.
HLAB — Harvey's Legal Agent Benchmark (Vals Index v2)333.8%
HLAB — Harvey's Legal Agent Benchmark (Vals Index v2) v2 ↗ · Published board — Long-horizon legal work product creation. Vals AI's run of Harvey's Legal Agent Benchmark, reported as accuracy — not comparable with Artificial Analysis' Harvey LAB-AA row.
AA Agentic Index6827.7
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
SciCode (AA subproblems) v1.0.16350.8%
SciCode (AA subproblems) v1.0.1 ↗ · Published board — Tests scientific Python programming with scientist-annotated background information.
Vibe Code Bench (Vals Index v2)2349.9%
Vibe Code Bench (Vals Index v2) v2 ↗ · Published board — End-to-end app-building tasks.
Code Migration (Vals Index v2 subset)2526.2%
Code Migration (Vals Index v2 subset) v2 ↗ · Published board — Porting projects to another language, including COBOL modernization.
SWE-bench Verified (Epoch AI run)6377.6%
SWE-bench Verified (Epoch AI run) published 2026-09-18 ↗ · Published board — Epoch AI's own inspect-ai runs of SWE-bench Verified, the human-validated GitHub issue-resolution set.
AA Coding Index6959.4
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
ApprenticeBench API cost per task (NeoCognition)88$0.46
ApprenticeBench API cost per task (NeoCognition) published 2026-09-14 ↗ · Claude Code — ApprenticeBench's published USD cost per task for each API-board model-harness-effort configuration on the 100-task accounts-payable job.
Vals Index v2 cost per test (Vals AI)83$0.9
Vals Index v2 cost per test (Vals AI) v2 ↗ · Published board — Vals AI's published USD cost per test for each model on the Vals Index v2.
Instruction-following
IFBench (AA single-turn)9676.5%
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)8937.5%
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 Index71-10.7
AA-Omniscience Index published 2026-09-10 ↗ · Published board — Tests factual reliability while rewarding correct answers and penalizing hallucinations.
Legal Research Bench (Vals Index v2)1323.1%
Legal Research Bench (Vals Index v2) v2 ↗ · Published board — Case and statute research with citation-backed answers.
SimpleQA Verified (run by Epoch AI)3947.0%
SimpleQA Verified (run by Epoch AI) published 2026-09-16 ↗ · Published board — Short fact-seeking questions answered without tools, testing whether a model knows a fact rather than guessing; Google DeepMind's cleaned version of OpenAI's SimpleQA, run by Epoch AI.
Long-context
GDP.pdf (AA)6113.4%
GDP.pdf (AA) published 2026-09-10 ↗ · Published board — Tests professional reasoning over long PDFs with AA document preparation and grading.
AA-LCR v1.17774.7%
AA-LCR v1.1 v1.1 ↗ · Published board — Tests reasoning across multiple long documents with corrected answer keys and grading.
MLCR-AA7321.1%
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)1845.3%
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)02.4%
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)3820.0%
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.
AA Intelligence Index8830.9
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)8812.9%
CritPt (AA) published 2026-09-10 ↗ · Published board — Tests research-level physics reasoning with Python, symbolic and numerical answers.
GPQA Diamond (AA)8688.8%
GPQA Diamond (AA) published 2026-09-10 ↗ · Published board — Tests graduate-level biology, physics and chemistry knowledge on the Diamond subset.
GPQA Diamond (Epoch AI run)5989.6%
GPQA Diamond (Epoch AI run) published 2026-09-18 ↗ · Published board — Epoch AI's own inspect-ai runs of GPQA Diamond, the 198-question graduate-level science multiple-choice set.
Tool-use
AutomationBench-AA v1.0.68456.3%
AutomationBench-AA v1.0.6 ↗ · Published board — Tests multi-app SaaS workflows through REST tools on a held-out AutomationBench split.
EnterpriseOps-Gym-AA4740.4%
EnterpriseOps-Gym-AA published 2026-09-10 ↗ · Published board — Tests enterprise workflows through MCP tools against resettable application environments.
τ²-Bench Telecom (AA)9796.2%
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) v1.0.16930.1%
τ³-Banking (AA) v1.0.1 ↗ · Published board — Tests banking support agents that retrieve policies and change account state through tools.
Excel Modeling Benchmark (Vals Index v2)1651.6%
Excel Modeling Benchmark (Vals Index v2) v2 ↗ · Published board — Building and editing financial models in spreadsheets.
Unusual results
1 threshold-crossing signal flagged · 37 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 weak FrontierMath Tier 4 v2 (Epoch AI)
Why
Observed: 0.02439 fractionPeer mean 0.49723 · peer sd 0.29908 · n 33 · families 29Directed z -1.581 · baseline z 0.312 · gap -1.893 · profile n 360.02439 fractionmeasuredobserved 2026-09-16epoch.ai ↗Evidence
Axis: FrontierMath Tier 4 v2 (Epoch AI) · v2 · Published boardExact value:0.024390243902439025fractionObserved: 2026-09-16T09:43:00Z · publication date: not recordedObservation id:public:0ea3cf191b80cdaa6393c40d
Missing coverage · 104 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 Pro 0424 (Reasoning, Max Effort) | 59.4 | 30.9 |
| DeepSeek V4 Pro 0424 (Reasoning, High Effort) | 58.7 | 30.1 |
| DeepSeek V4 Pro 0424 (Non-reasoning) | — | 20.8 |
Token offers by platform · 12 offers (Adjusted $/task)
Click any underlined price to see how it is estimated and where each input comes from. How we calculate adjusted cost.
12 offers within the active global filters; “—” means the catalog is active but no public token price is available.
OpenRouter (9)
| DigitalOcean | globaldigitalocean | $1.04 raw in $/1M | $2.09 raw out $/1M | |
| DeepInfra | globaldeepinfra/fp8 | $1.30 raw in $/1M | $2.60 raw out $/1M | |
| SiliconFlow | globalsiliconflow/fp8 | $1.50 raw in $/1M | $3.13 raw out $/1M | |
| Novita | globalnovita/fp8 | $1.60 raw in $/1M | $3.20 raw out $/1M | |
| Parasail | globalparasail/fp8 | $1.74 raw in $/1M | $3.48 raw out $/1M | |
| BaseTen | globalbaseten/fp4 | $1.74 raw in $/1M | $3.48 raw out $/1M | |
| NextBit | globalnextbit/fp8EU | $1.91 raw in $/1M | $3.83 raw out $/1M | |
| Azure | globalazure/us | $1.91 raw in $/1M | $3.83 raw out $/1M | |
| Venice | globalvenice | $1.65 raw in $/1M | $3.30 raw out $/1M |
Azure AI Foundry (2)
| Azure AI Foundry | globalazure directEU equivalent | $1.74 raw in $/1M | $3.48 raw out $/1M | |
| Azure AI Foundry | usfireworks | $1.93 raw in $/1M | $3.83 raw out $/1M |
Nebius (1)
| Nebius | uk | $1.75 raw in $/1M | $3.50 raw out $/1M |