DeepSeek
DeepSeek V4 Pro (0813)
DeepSeek V4 Pro (0813) is a model with open weights from DeepSeek. On the Vals AI Legal Research Bench it reaches 40.87 percent all-pass, position 33 of 91, within a standard error of ±3.42 percentage points at $1.09 per task, as at 9 November 2026 [1]. It does not pass the compliance gate: DeepSeek own API: personal data is "directly collect, process and stor in People's Republic of China" (privacy policy) and the terms are governed by PRC law; no EU contracting party or EU processing.
- Status unknown
- Open weights
- 13 August 2026
- PrudentScore
- -No score: the gate is not open
- Compliance gate
- RejectedDeepSeek own API: personal data is "directly collect, process and stor in People's Republic of China" (privacy policy) and the terms are governed by PRC law; no EU contracting party or EU processing
- Cost per task
- $1.09Vals AI, per completed task [1]
01
Compliance gate
Why
- DeepSeek own API: personal data is "directly collect, process and stor in People's Republic of China" (privacy policy) and the terms are governed by PRC law; no EU contracting party or EU processing.
The gate only opens when all three requirements are covered: processing in the EU, a contracting party in the EU or EEA, and a contractual exclusion of training on customer data. The gate tests a route, not a model name: the same model can pass through one provider and fail through another. Where a provider publishes no figure, we give no estimate.
02
Routes and EU processing
The gate tests a route (processor, region and contract), not a model name. Per route: processing in the EU, the contracting party and training on customer data.
No route has been recorded in the register for this model yet.
03
Scores per benchmark
Every measurement with its source, measurement date and the day we read it. The position counts only the models measured on the same benchmark and version.
- Legal Research BenchVersion 1 · Counts towards the PrudentScore40.87%± 3.4233 of 91
Vals AI, Legal Research Bench, v1, 9 November 2026 · Source · Measured 9 November 2026 · Read 10 November 2026 · cost per task $1.09
- Harvey LAB (Vals implementation)Version 1.110.83%± 2.7220 of 36
Vals AI, Harvey LAB (Vals implementation), v1.1, 9 November 2026 · Source · Measured 9 November 2026 · Read 10 November 2026 · cost per task $0.80
- Harvey LAB (Vals implementation)Version 1 · Counts towards the PrudentScore7.50%± 2.1529 of 80
Vals AI, Harvey LAB (Vals implementation), v1, 18 October 2026 · Source · Measured 18 October 2026 · Read 10 November 2026 · cost per task $0.17
- LegalBench (Vals leaderboard)Version 182.36%± 0.4468 of 113
Vals AI, LegalBench (Vals leaderboard), v1, 13 October 2026 · Source · Measured 13 October 2026 · Read 10 November 2026
- CaseLaw v2Not measured
- TaxEval v2Version 273.06%± 0.8751 of 108
Vals AI, TaxEval v2, v2, 1 September 2026 · Source · Measured 1 September 2026 · Read 10 November 2026
- Tax Agent BenchVersion 126.76%± 3.0940 of 82
Vals AI, Tax Agent Bench, v1, 9 November 2026 · Source · Measured 9 November 2026 · Read 10 November 2026 · cost per task $0.73
- CorpFin v2Version 265.42%± 0.9429 of 108
Vals AI, CorpFin v2, v2, 12 August 2026 · Source · Measured 12 August 2026 · Read 10 November 2026
- Immigration BenchVersion 161.66%± 1.6824 of 26
Vals AI, Immigration Bench, v1, 9 November 2026 · Source · Measured 9 November 2026 · Read 10 November 2026 · cost per task $0.05
- Access to JusticeNot measured
- Public Benefits BenchNot measured
- Vals Legal IndexVersion 169.01%± 1.7720 of 36
Vals AI, Vals Legal Index, v1, 9 November 2026 · Source · Measured 9 November 2026 · Read 10 November 2026 · cost per task $0.87
- Vals IndexVersion 2.252.97%± 1.0426 of 35
Vals AI, Vals Index, v2.2, 9 November 2026 · Source · Measured 9 November 2026 · Read 10 November 2026 · cost per task $2.50
- Vals IndexVersion 2.147.63%± 1.1238 of 50
Vals AI, Vals Index, v2.1, 18 October 2026 · Source · Measured 18 October 2026 · Read 10 November 2026 · cost per task $3.35
- GPQA Diamond (Vals-run)Version 192.42%± 2.0216 of 109
Vals AI, GPQA Diamond (Vals-run), v1, 1 September 2026 · Source · Measured 1 September 2026 · Read 10 November 2026
- MMLU Pro (Vals-run)Version 186.97%± 0.3436 of 110
Vals AI, MMLU Pro (Vals-run), v1, 1 September 2026 · Source · Measured 1 September 2026 · Read 10 November 2026
- Artificial Analysis Intelligence IndexVersion 4.3.2 · Counts towards the PrudentScore
Artificial Analysis Intelligence Index v4.3.2: 36.0. Source: Artificial Analysis (artificialanalysis.ai), accessed 1 October 2026 [37].
Artificial Analysis, Artificial Analysis Intelligence Index, v4.3.2, 1 October 2026 · Source · Measured 1 October 2026 · Read 1 October 2026
Source: Vals AI (Legal Research Bench, Harvey LAB (Vals implementation), LegalBench (Vals leaderboard), TaxEval v2, …) · Licence: CC BY 4.0 · Adaptation: Prudai selected the models, translated the explanations, added the gate verdict and the PrudentScore and rounded figures to two decimals.
The PrudentScore is a composition by Prudai B.V. based on publicly published figures and does not represent the view or endorsement of Vals AI, Harvey or Artificial Analysis. Figures from Artificial Analysis appear in running text only, with attribution and a link, as that party's terms require [9].
04
Key facts
- Developer
- DeepSeek
- Model family
- DeepSeek
- Release date
- 13 August 2026
- Status
- Status unknown
- Context window
- 1M tokens
- Max output tokens
- 384K tokens
- List price
- $1.32 input · $3.96 outputper million tokens · Read 10 November 2026
- Weights
- Open
- = not yet recorded in the register.
05
Frequently asked questions about this model
Does DeepSeek V4 Pro (0813) pass the compliance gate for legal work?
No. DeepSeek own API: personal data is "directly collect, process and stor in People's Republic of China" (privacy policy) and the terms are governed by PRC law; no EU contracting party or EU processing. The gate tests a route, not a model name; the sources are on this page.
What does DeepSeek V4 Pro (0813) cost per task?
Vals computes $1.09 per completed task on the Legal Research Bench [1]. The list price is $1.32 per million input tokens and $3.96 per million output tokens.
How does DeepSeek V4 Pro (0813) score on legal research?
40.87 percent all-pass on the Vals AI Legal Research Bench, position 33 of 91 measured models, as at 9 November 2026 [1]. That benchmark measures US law; an independent, published benchmark for Dutch legal work does not exist yet.
Related models
- Hy4
- Muse Spark 1.3
- DeepSeek V4.1 Flash 1017
- DeepSeek V4.1 Flash
- DeepSeek V4 Flash 0731
- DeepSeek V4 Pro (2026-04-23)
Claude and Anthropic, GPT and OpenAI, Gemini and Google, Grok and xAI, Kimi and Moonshot AI, Muse and Meta, Mistral, DeepSeek, GLM and Z.ai, Harvey, Vals AI and Artificial Analysis are trademarks of their respective owners. They are named for identification only and this implies no partnership, sponsorship or endorsement.
Brand marks appear for identification only and imply no partnership, sponsorship or endorsement.