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

DeepSeek V4 Pro 0813 (Reasoning, Max Effort)

open weights★ featured
DeepSeek · released 2026-08-13 · 21 recorded token offers

Top 5 cheapest providers (Adjusted $/task)

Within the active global provider, residency and confidentiality filters.

#ProviderPlatformRaw input $/1MRaw output $/1MAdjusted $/task
1NovitaOpenRouter$0.990$2.97
2GMICloudOpenRouter$1.06$3.17
3IonstreamOpenRouter$1.10$3.30
4NextBitOpenRouter$1.12$3.37
5DeepInfraOpenRouter$1.30$2.60

Benchmarks

Composite65.4
Mean-imputed base61.4
Dominance adjustment+4.0
Composite evidence3/5
AA Coding · unversioned snapshot 2026-09-1068.8
AA Coding Agent · v1.4 · 2026-09-0942.8
AA Intelligence · unversioned snapshot 2026-09-1036.3
DesignArena Frontend · unversioned snapshot 2026-09-10
DesignArena Full-Stack · unversioned snapshot 2026-09-10
Output speed (t/s)60

MODEL EVIDENCE

Benchmark sheet

15 / 73 registered benchmark versions covered · 17 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 · 16 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-Briefcase

Version snapshot-2026-09-10

Published board

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

1264.67 Elomeasuredobserved 2026-09-10artificialanalysis.ai
Evidence
Axis: AA-Briefcase · snapshot-2026-09-10 · Published board
Exact value: 1264.67 Elo
Observed: 2026-09-10T21:47:16.627Z · publication date: not recorded
Observation id: aa:83173329-c09a-41f1-a028-a282a5f908d7:briefcaseBreakdown.overall.elo
GDPval-AA v2

Version 2

Published board

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

1493.31 Elomeasuredobserved 2026-09-10artificialanalysis.ai
Evidence
Axis: GDPval-AA v2 · 2 · Published board
Exact value: 1493.31 Elo
Observed: 2026-09-10T21:47:16.627Z · publication date: not recorded
Observation id: aa:83173329-c09a-41f1-a028-a282a5f908d7:gdpval
Terminal-Bench v2.1 (AA)

Version 2.1

Published board

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

0.78652 fractionmeasuredobserved 2026-09-10artificialanalysis.ai
Evidence
Axis: Terminal-Bench v2.1 (AA) · 2.1 · Published board
Exact value: 0.786516853932584 fraction
Observed: 2026-09-10T21:47:16.627Z · publication date: not recorded
Observation id: aa:83173329-c09a-41f1-a028-a282a5f908d7: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.

0.14141 fractionmeasuredobserved 2026-09-10artificialanalysis.ai
Evidence
Axis: Terminal-Bench v4.0 (AA) · 4.0 · Published board
Exact value: 0.141414141414141 fraction
Observed: 2026-09-10T21:47:16.627Z · publication date: not recorded
Observation id: aa:83173329-c09a-41f1-a028-a282a5f908d7: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.

0.51042 fractionmeasuredobserved 2026-09-10artificialanalysis.ai
Evidence
Axis: SciCode (AA subproblems) · 1.0.1 · Published board
Exact value: 0.510416666666667 fraction
Observed: 2026-09-10T21:47:16.627Z · publication date: not recorded
Observation id: aa:83173329-c09a-41f1-a028-a282a5f908d7: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.

68.8 pointsmeasuredobserved 2026-09-10artificialanalysis.ai
Evidence
Axis: AA Coding Index · snapshot-2026-09-10 (unversioned) · Published board
Exact value: 68.8 points
Observed: 2026-09-10 · publication date: not recorded
Observation id: legacy:aa_coding_index:deepseek-v4-pro-0813::max
Protocol: inspect · file data/raw/artificialanalysis.json

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.

0.4101 fractionmeasuredobserved 2026-09-10artificialanalysis.ai
Evidence
Axis: Humanity's Last Exam (AA text-only) · snapshot-2026-09-10 · Published board
Exact value: 0.410101946246525 fraction
Observed: 2026-09-10T21:47:16.627Z · publication date: not recorded
Observation id: aa:83173329-c09a-41f1-a028-a282a5f908d7:hle
AA-Omniscience Index

Version snapshot-2026-09-10

Published board

Tests factual reliability while rewarding correct answers and penalizing hallucinations.

0.83333 pointsmeasuredobserved 2026-09-10artificialanalysis.ai
Evidence
Axis: AA-Omniscience Index · snapshot-2026-09-10 · Published board
Exact value: 0.833333333333333 points
Observed: 2026-09-10T21:47:16.627Z · publication date: not recorded
Observation id: aa:83173329-c09a-41f1-a028-a282a5f908d7: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.

0.114 fractionmeasuredobserved 2026-09-10artificialanalysis.ai
Evidence
Axis: GDP.pdf (AA) · snapshot-2026-09-10 · Published board
Exact value: 0.114 fraction
Observed: 2026-09-10T21:47:16.627Z · publication date: not recorded
Observation id: aa:83173329-c09a-41f1-a028-a282a5f908d7:gdpPdfAllPass
AA-LCR v1.1

Version 1.1

Published board

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

0.80333 fractionmeasuredobserved 2026-09-10artificialanalysis.ai
Evidence
Axis: AA-LCR v1.1 · 1.1 · Published board
Exact value: 0.803333333333333 fraction
Observed: 2026-09-10T21:47:16.627Z · publication date: not recorded
Observation id: aa:83173329-c09a-41f1-a028-a282a5f908d7:lcr
MLCR-AA

Version snapshot-2026-09-10

Published board

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

0.17778 fractionmeasuredobserved 2026-09-10artificialanalysis.ai
Evidence
Axis: MLCR-AA · snapshot-2026-09-10 · Published board
Exact value: 0.177777777777778 fraction
Observed: 2026-09-10T21:47:16.627Z · publication date: not recorded
Observation id: aa:83173329-c09a-41f1-a028-a282a5f908d7: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.

36.3 pointsmeasuredobserved 2026-09-10artificialanalysis.ai
Evidence
Axis: AA Intelligence Index · snapshot-2026-09-10 (unversioned) · Published board
Exact value: 36.3 points
Observed: 2026-09-10 · publication date: not recorded
Observation id: legacy:aa_intelligence_index:deepseek-v4-pro-0813::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.

0.18 fractionmeasuredobserved 2026-09-10artificialanalysis.ai
Evidence
Axis: CritPt (AA) · snapshot-2026-09-10 · Published board
Exact value: 0.18 fraction
Observed: 2026-09-10T21:47:16.627Z · publication date: not recorded
Observation id: aa:83173329-c09a-41f1-a028-a282a5f908d7:critpt
GPQA Diamond (AA)

Version snapshot-2026-09-10

Published board

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

0.92828 fractionmeasuredobserved 2026-09-10artificialanalysis.ai
Evidence
Axis: GPQA Diamond (AA) · snapshot-2026-09-10 · Published board
Exact value: 0.928282828282828 fraction
Observed: 2026-09-10T21:47:16.627Z · publication date: not recorded
Observation id: aa:83173329-c09a-41f1-a028-a282a5f908d7: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.

0.56712 fractionmeasuredobserved 2026-09-10artificialanalysis.ai
Evidence
Axis: AutomationBench-AA · 1.0.6 · Published board
Exact value: 0.5671165546344002 fraction
Observed: 2026-09-10T21:47:16.627Z · publication date: not recorded
Observation id: aa:83173329-c09a-41f1-a028-a282a5f908d7:automationBenchPartialScore
EnterpriseOps-Gym-AA

Version snapshot-2026-09-10

Published board

Tests enterprise workflows through MCP tools against resettable application environments.

0.49597 fractionmeasuredobserved 2026-09-10artificialanalysis.ai
Evidence
Axis: EnterpriseOps-Gym-AA · snapshot-2026-09-10 · Published board
Exact value: 0.4959713518352731 fraction
Observed: 2026-09-10T21:47:16.627Z · publication date: not recorded
Observation id: aa:83173329-c09a-41f1-a028-a282a5f908d7:enterpriseOpsGym
τ³-Banking (AA)

Version 1.0.1

Published board

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

0.39588 fractionmeasuredobserved 2026-09-10artificialanalysis.ai
Evidence
Axis: τ³-Banking (AA) · 1.0.1 · Published board
Exact value: 0.395876288659794 fraction
Observed: 2026-09-10T21:47:16.627Z · publication date: not recorded
Observation id: aa:83173329-c09a-41f1-a028-a282a5f908d7:tauBanking
Missing coverage · 60 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 — 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.

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

OpenRouter (15)

Novitaglobalnovita/fp8$0.990 raw in $/1M$2.97 raw out $/1M
GMICloudglobalgmicloud/fp8$1.06 raw in $/1M$3.17 raw out $/1M
Ionstreamglobalionstream/fp4$1.10 raw in $/1M$3.30 raw out $/1M
NextBitglobalnextbit/fp8EU$1.12 raw in $/1M$3.37 raw out $/1M
DeepInfraglobaldeepinfra/fp8$1.30 raw in $/1M$2.60 raw out $/1M
CoreWeaveglobalcoreweave/fp8$1.31 raw in $/1M$3.96 raw out $/1M
Nebiusglobalnebius/fp8$1.32 raw in $/1M$3.96 raw out $/1M
Sail Researchglobalsail-research/fp4$1.32 raw in $/1M$3.96 raw out $/1M
BaseTenglobalbaseten/fp4$1.32 raw in $/1M$3.96 raw out $/1M
Parasailglobalparasail/fp8$1.32 raw in $/1M$3.96 raw out $/1M
Togetherglobaltogether$1.32 raw in $/1M$3.96 raw out $/1M
DigitalOceanglobaldigitalocean$1.32 raw in $/1M$3.96 raw out $/1M
Cloudflareglobalcloudflare$1.32 raw in $/1M$3.96 raw out $/1M
Fireworksglobalfireworks$1.32 raw in $/1M$3.96 raw out $/1M
PhalaglobalphalaTEE$1.45 raw in $/1M$4.36 raw out $/1M

TensorX (1)

TensorXeuEU$2.00 raw in $/1M$4.00 raw out $/1M
Benchmark Heaven — Model benchmarks & costs