Benchmark Heaven
Price & provider filters · adjusted costs
Global
Applies to price views & model offers; benchmark evidence stays unfiltered
← All models

DeepSeek V4 Pro (Reasoning, Max Effort)

open weights★ featured
DeepSeek · released 2026-04-24 · 18 recorded token offers

Top 5 cheapest providers (Adjusted $/task)

Within the active global provider, residency and confidentiality filters.

#ProviderPlatformRaw input $/1MRaw output $/1MAdjusted $/task
1DigitalOceanOpenRouter$0.870$1.74
2GMICloudOpenRouter$0.957$1.91
3FireworksOpenRouter$1.20$1.20
4DeepInfraOpenRouter$1.30$2.60
5NovitaOpenRouter$1.60$3.20

Benchmarks

Composite60.2
Mean-imputed base50.9
Dominance adjustment+9.3
Composite evidence2/5
AA Coding · unversioned snapshot 2026-09-1059.4
AA Coding Agent · v1.4 · 2026-09-09
AA Intelligence · unversioned snapshot 2026-09-1030.9
DesignArena Frontend · unversioned snapshot 2026-09-10
DesignArena Full-Stack · unversioned snapshot 2026-09-10
Output speed (t/s)61

MODEL EVIDENCE

Benchmark sheet

22 / 73 registered benchmark versions covered · 24 observations including existing index snapshots.

Compare this model ↗
Composite retains Coding Agent v1.4 · source 2026-09-09

The five Composite inputs remain unchanged. Its Coding Agent input is the median across complete harness results in the retained v1.4 snapshot from 2026-09-09. Artificial Analysis now publishes v1.5, with different components. Explore current v1.5 separately. Dated snapshot labels on other indices identify unversioned source captures, not a verified semantic version.

Profile signals

No threshold-crossing signal · 23 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.

Protocol-compatible measured/vendor divergences

No verified protocol-compatible vendor/measured pair is available for this model; agreement cannot be assessed.

Agentic

Agentic: every observation for this exact model configuration
Benchmark / versionEvaluation groupScore / provenance
AA-AnalystAgent

Version snapshot-2026-09-10

Published board

Tests analyst tasks using agentic Python execution across fourteen domains.

0.1875 fractionmeasuredobserved 2026-09-10artificialanalysis.ai
Evidence
Axis: AA-AnalystAgent · snapshot-2026-09-10 · Published board
Exact value: 0.1875 fraction
Observed: 2026-09-10T21:47:16.627Z · publication date: not recorded
Observation id: aa:bf220674-68bd-43cc-a1b8-ce5ed4d2f18d:analystAgent
APEX-Agents-AA

Version snapshot-2026-09-10

Published board

Tests professional-service tasks that require agents to produce locally graded deliverables.

0.24263 fractionmeasuredobserved 2026-09-10artificialanalysis.ai
Evidence
Axis: APEX-Agents-AA · snapshot-2026-09-10 · Published board
Exact value: 0.242625368731563 fraction
Observed: 2026-09-10T21:47:16.627Z · publication date: not recorded
Observation id: aa:bf220674-68bd-43cc-a1b8-ce5ed4d2f18d:apexAgents
AA-Briefcase

Version snapshot-2026-09-10

Published board

Tests multi-week professional knowledge-work projects with linked tasks and large source collections.

924.56 Elomeasuredobserved 2026-09-10artificialanalysis.ai
Evidence
Axis: AA-Briefcase · snapshot-2026-09-10 · Published board
Exact value: 924.56 Elo
Observed: 2026-09-10T21:47:16.627Z · publication date: not recorded
Observation id: aa:bf220674-68bd-43cc-a1b8-ce5ed4d2f18d:briefcaseBreakdown.overall.elo
GDPval-AA v2

Version 2

Published board

Tests professional knowledge-work deliverables across occupations using AA's Stirrup harness.

1223.37 Elomeasuredobserved 2026-09-10artificialanalysis.ai
Evidence
Axis: GDPval-AA v2 · 2 · Published board
Exact value: 1223.37 Elo
Observed: 2026-09-10T21:47:16.627Z · publication date: not recorded
Observation id: aa:bf220674-68bd-43cc-a1b8-ce5ed4d2f18d:gdpval
Harvey LAB-AA

Version snapshot-2026-09-10

Published board

Tests legal-work deliverables across practice areas on Harvey's private task set.

0.84397 fractionmeasuredobserved 2026-09-10artificialanalysis.ai
Evidence
Axis: Harvey LAB-AA · snapshot-2026-09-10 · Published board
Exact value: 0.843971631205674 fraction
Observed: 2026-09-10T21:47:16.627Z · publication date: not recorded
Observation id: aa:bf220674-68bd-43cc-a1b8-ce5ed4d2f18d:harveyLab
ITBench-AA

Version snapshot-2026-09-10

Published board

Tests root-cause diagnosis from offline Kubernetes incident snapshots.

0.38324 fractionmeasuredobserved 2026-09-10artificialanalysis.ai
Evidence
Axis: ITBench-AA · snapshot-2026-09-10 · Published board
Exact value: 0.383239171374765 fraction
Observed: 2026-09-10T21:47:16.627Z · publication date: not recorded
Observation id: aa:bf220674-68bd-43cc-a1b8-ce5ed4d2f18d:itBenchSre
Terminal-Bench Hard (AA)

Version 74221fb

Published board

Tests a pinned 44-task hard subset of terminal-based work using Terminus 2.

0.46212 fractionmeasuredobserved 2026-09-10artificialanalysis.ai
Evidence
Axis: Terminal-Bench Hard (AA) · 74221fb · Published board
Exact value: 0.462121212121212 fraction
Observed: 2026-09-10T21:47:16.627Z · publication date: not recorded
Observation id: aa:bf220674-68bd-43cc-a1b8-ce5ed4d2f18d:terminalbenchHard
Terminal-Bench v2.1 (AA)

Version 2.1

Published board

Tests terminal-based work on the 89-task verified refresh using Terminus 2.

0.64045 fractionmeasuredobserved 2026-09-10artificialanalysis.ai
Evidence
Axis: Terminal-Bench v2.1 (AA) · 2.1 · Published board
Exact value: 0.640449438202247 fraction
Observed: 2026-09-10T21:47:16.627Z · publication date: not recorded
Observation id: aa:bf220674-68bd-43cc-a1b8-ce5ed4d2f18d:terminalbenchV21
Terminal-Bench v4.0 (AA)

Version 4.0

Published board

Tests terminal-based work on the 66-task release using mini-SWE-agent v2.4.6.

0.14646 fractionmeasuredobserved 2026-09-10artificialanalysis.ai
Evidence
Axis: Terminal-Bench v4.0 (AA) · 4.0 · Published board
Exact value: 0.146464646464646 fraction
Observed: 2026-09-10T21:47:16.627Z · publication date: not recorded
Observation id: aa:bf220674-68bd-43cc-a1b8-ce5ed4d2f18d:terminalbenchV40

Coding

Coding: every observation for this exact model configuration
Benchmark / versionEvaluation groupScore / provenance
SciCode (AA subproblems)

Version 1.0.1

Published board

Tests scientific Python programming with scientist-annotated background information.

0.5081 fractionmeasuredobserved 2026-09-10artificialanalysis.ai
Evidence
Axis: SciCode (AA subproblems) · 1.0.1 · Published board
Exact value: 0.508101851851852 fraction
Observed: 2026-09-10T21:47:16.627Z · publication date: not recorded
Observation id: aa:bf220674-68bd-43cc-a1b8-ce5ed4d2f18d:scicode
AA Coding Index

Version snapshot-2026-09-10 (unversioned)

Published board

Published AA index from the retained API snapshot. No verified semantic version was supplied.

59.4 pointsmeasuredobserved 2026-09-10artificialanalysis.ai
Evidence
Axis: AA Coding Index · snapshot-2026-09-10 (unversioned) · Published board
Exact value: 59.4 points
Observed: 2026-09-10 · publication date: not recorded
Observation id: legacy:aa_coding_index:deepseek-v4-pro::max
Protocol: inspect · file data/raw/artificialanalysis.json

Instruction-following

Instruction-following: every observation for this exact model configuration
Benchmark / versionEvaluation groupScore / provenance
IFBench (AA single-turn)

Version snapshot-2026-09-10

Published board

Tests precise single-turn instructions with deterministic rule checks.

0.76463 fractionmeasuredobserved 2026-09-10artificialanalysis.ai
Evidence
Axis: IFBench (AA single-turn) · snapshot-2026-09-10 · Published board
Exact value: 0.764625850340136 fraction
Observed: 2026-09-10T21:47:16.627Z · publication date: not recorded
Observation id: aa:bf220674-68bd-43cc-a1b8-ce5ed4d2f18d:ifbench

Knowledge

Knowledge: every observation for this exact model configuration
Benchmark / versionEvaluation groupScore / provenance
Humanity's Last Exam (AA text-only)

Version snapshot-2026-09-10

Published board

Tests expert-level knowledge on AA's text-only Humanity's Last Exam subset.

0.37535 fractionmeasuredobserved 2026-09-10artificialanalysis.ai
Evidence
Axis: Humanity's Last Exam (AA text-only) · snapshot-2026-09-10 · Published board
Exact value: 0.375347544022243 fraction
Observed: 2026-09-10T21:47:16.627Z · publication date: not recorded
Observation id: aa:bf220674-68bd-43cc-a1b8-ce5ed4d2f18d:hle
AA-Omniscience Index

Version snapshot-2026-09-10

Published board

Tests factual reliability while rewarding correct answers and penalizing hallucinations.

-10.73333 pointsmeasuredobserved 2026-09-10artificialanalysis.ai
Evidence
Axis: AA-Omniscience Index · snapshot-2026-09-10 · Published board
Exact value: -10.7333333333333 points
Observed: 2026-09-10T21:47:16.627Z · publication date: not recorded
Observation id: aa:bf220674-68bd-43cc-a1b8-ce5ed4d2f18d:omniscience

Long-context

Long-context: every observation for this exact model configuration
Benchmark / versionEvaluation groupScore / provenance
GDP.pdf (AA)

Version snapshot-2026-09-10

Published board

Tests professional reasoning over long PDFs with AA document preparation and grading.

0.134 fractionmeasuredobserved 2026-09-10artificialanalysis.ai
Evidence
Axis: GDP.pdf (AA) · snapshot-2026-09-10 · Published board
Exact value: 0.134 fraction
Observed: 2026-09-10T21:47:16.627Z · publication date: not recorded
Observation id: aa:bf220674-68bd-43cc-a1b8-ce5ed4d2f18d:gdpPdfAllPass
AA-LCR v1.1

Version 1.1

Published board

Tests reasoning across multiple long documents with corrected answer keys and grading.

0.74667 fractionmeasuredobserved 2026-09-10artificialanalysis.ai
Evidence
Axis: AA-LCR v1.1 · 1.1 · Published board
Exact value: 0.746666666666667 fraction
Observed: 2026-09-10T21:47:16.627Z · publication date: not recorded
Observation id: aa:bf220674-68bd-43cc-a1b8-ce5ed4d2f18d:lcr
MLCR-AA

Version snapshot-2026-09-10

Published board

Tests medical-record synthesis and reasoning across long, fragmented case documents.

0.21111 fractionmeasuredobserved 2026-09-10artificialanalysis.ai
Evidence
Axis: MLCR-AA · snapshot-2026-09-10 · Published board
Exact value: 0.211111111111111 fraction
Observed: 2026-09-10T21:47:16.627Z · publication date: not recorded
Observation id: aa:bf220674-68bd-43cc-a1b8-ce5ed4d2f18d:mlcrOverall

Reasoning

Reasoning: every observation for this exact model configuration
Benchmark / versionEvaluation groupScore / provenance
AA Intelligence Index

Version snapshot-2026-09-10 (unversioned)

Published board

Published AA index from the retained API snapshot. No verified semantic version was supplied.

30.9 pointsmeasuredobserved 2026-09-10artificialanalysis.ai
Evidence
Axis: AA Intelligence Index · snapshot-2026-09-10 (unversioned) · Published board
Exact value: 30.9 points
Observed: 2026-09-10 · publication date: not recorded
Observation id: legacy:aa_intelligence_index:deepseek-v4-pro::max
Protocol: inspect · file data/raw/artificialanalysis.json

Science

Science: every observation for this exact model configuration
Benchmark / versionEvaluation groupScore / provenance
CritPt (AA)

Version snapshot-2026-09-10

Published board

Tests research-level physics reasoning with Python, symbolic and numerical answers.

0.12857 fractionmeasuredobserved 2026-09-10artificialanalysis.ai
Evidence
Axis: CritPt (AA) · snapshot-2026-09-10 · Published board
Exact value: 0.128571428571429 fraction
Observed: 2026-09-10T21:47:16.627Z · publication date: not recorded
Observation id: aa:bf220674-68bd-43cc-a1b8-ce5ed4d2f18d:critpt
GPQA Diamond (AA)

Version snapshot-2026-09-10

Published board

Tests graduate-level biology, physics and chemistry knowledge on the Diamond subset.

0.88788 fractionmeasuredobserved 2026-09-10artificialanalysis.ai
Evidence
Axis: GPQA Diamond (AA) · snapshot-2026-09-10 · Published board
Exact value: 0.887878787878788 fraction
Observed: 2026-09-10T21:47:16.627Z · publication date: not recorded
Observation id: aa:bf220674-68bd-43cc-a1b8-ce5ed4d2f18d:gpqa

Tool-use

Tool-use: every observation for this exact model configuration
Benchmark / versionEvaluation groupScore / provenance
AutomationBench-AA

Version 1.0.6

Published board

Tests multi-app SaaS workflows through REST tools on a held-out AutomationBench split.

0.5629 fractionmeasuredobserved 2026-09-10artificialanalysis.ai
Evidence
Axis: AutomationBench-AA · 1.0.6 · Published board
Exact value: 0.5628968557434271 fraction
Observed: 2026-09-10T21:47:16.627Z · publication date: not recorded
Observation id: aa:bf220674-68bd-43cc-a1b8-ce5ed4d2f18d:automationBenchPartialScore
EnterpriseOps-Gym-AA

Version snapshot-2026-09-10

Published board

Tests enterprise workflows through MCP tools against resettable application environments.

0.40436 fractionmeasuredobserved 2026-09-10artificialanalysis.ai
Evidence
Axis: EnterpriseOps-Gym-AA · snapshot-2026-09-10 · Published board
Exact value: 0.40435690838555655 fraction
Observed: 2026-09-10T21:47:16.627Z · publication date: not recorded
Observation id: aa:bf220674-68bd-43cc-a1b8-ce5ed4d2f18d:enterpriseOpsGym
τ²-Bench Telecom (AA)

Version snapshot-2026-09-10

Published board

Tests dual-control telecom agents that coordinate tool use with a simulated user.

0.96199 fractionmeasuredobserved 2026-09-10artificialanalysis.ai
Evidence
Axis: τ²-Bench Telecom (AA) · snapshot-2026-09-10 · Published board
Exact value: 0.961988304093567 fraction
Observed: 2026-09-10T21:47:16.627Z · publication date: not recorded
Observation id: aa:bf220674-68bd-43cc-a1b8-ce5ed4d2f18d:tau2
τ³-Banking (AA)

Version 1.0.1

Published board

Tests banking support agents that retrieve policies and change account state through tools.

0.30103 fractionmeasuredobserved 2026-09-10artificialanalysis.ai
Evidence
Axis: τ³-Banking (AA) · 1.0.1 · Published board
Exact value: 0.301030927835052 fraction
Observed: 2026-09-10T21:47:16.627Z · publication date: not recorded
Observation id: aa:bf220674-68bd-43cc-a1b8-ce5ed4d2f18d:tauBanking
Missing coverage · 53 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

VariantCoding · snapshot 2026-09-10Intelligence · snapshot 2026-09-10
DeepSeek V4 Pro (Reasoning, Max Effort)59.430.9
DeepSeek V4 Pro (Reasoning, High Effort)58.730.1
DeepSeek V4 Pro (Non-reasoning)20.8

Token offers by platform — Adjusted $/task

Adjusted costs are modeled USD per task: AA output tokens × OpenRouter usage I/O (Chutes global fallback). These are general usage and benchmark proxies for coding-agent work. Missing AA data assumes 1,000 output tokens/task; unknown cache hit assumes 0%; unmeasured additional cache writes assume 0 tokens. Click any underlined price for exact inputs, dates and assumptions. Raw list prices use the selected fixed input/output blend, in USD per million tokens.

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

OpenRouter (11)

DigitalOceanglobaldigitalocean$0.870 raw in $/1M$1.74 raw out $/1M
GMICloudglobalgmicloud/fp8$0.957 raw in $/1M$1.91 raw out $/1M
DeepInfraglobaldeepinfra/fp8$1.30 raw in $/1M$2.60 raw out $/1M
Novitaglobalnovita/fp8$1.60 raw in $/1M$3.20 raw out $/1M
Veniceglobalvenice$1.65 raw in $/1M$3.30 raw out $/1M
AtlasCloudglobalatlas-cloud/fp4$1.68 raw in $/1M$3.38 raw out $/1M
BaseTenglobalbaseten/fp4$1.74 raw in $/1M$3.48 raw out $/1M
Parasailglobalparasail/fp8$1.74 raw in $/1M$3.48 raw out $/1M
NextBitglobalnextbit/fp8EU$1.80 raw in $/1M$3.55 raw out $/1M
Azureglobalazure/us$1.91 raw in $/1M$3.83 raw out $/1M
Fireworksglobalfireworks$1.20 raw in $/1M$1.20 raw out $/1M

Azure AI Foundry (2)

Azure AI Foundryglobalazure directEU equivalent$1.74 raw in $/1M$3.48 raw out $/1M
Azure AI Foundryusfireworks$1.93 raw in $/1M$3.83 raw out $/1M

Nebius (1)

Nebiusuk$1.75 raw in $/1M$3.50 raw out $/1M
Benchmark Heaven — Model benchmarks & costs