DeepSeek
DeepSeek V4.1 Flash
DeepSeek V4.1 Flash is a model with open weights from DeepSeek. On the Vals AI Legal Research Bench it reaches 41.35 percent all-pass, position 30 of 91, within a standard error of ±3.42 percentage points at $0.25 per task, as at 9 November 2026 [1]. It does not pass the compliance gate: No EU guarantee: Google Cloud Vertex AI: not in the EU or US column (global).
- Generally available
- Open weights
- 10 September 2026
- PrudentScore
- -No score: the gate is not open
- Compliance gate
- RejectedNo EU guarantee: Google Cloud Vertex AI: not in the EU or US column (global)
- Cost per task
- $0.25Vals AI, per completed task [1]
01
Compliance gate
Why
- No EU guarantee: Google Cloud Vertex AI: not in the EU or US column (global)
- 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.
| Processor | Region or deployment | EU processing | Source |
|---|---|---|---|
| Google Cloud Vertex AI | not in the EU or US column (global) | No | SourceRead 10 November 2026 |
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 PrudentScore41.35%± 3.4230 of 91
Vals AI, Legal Research Bench, v1, 9 November 2026 · Source · Measured 9 November 2026 · Read 10 November 2026 · cost per task $0.25
- Harvey LAB (Vals implementation)Version 1 · Counts towards the PrudentScore6.67%± 1.8331 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 183.28%± 0.4654 of 113
Vals AI, LegalBench (Vals leaderboard), v1, 13 October 2026 · Source · Measured 13 October 2026 · Read 10 November 2026
- CaseLaw v2Not measured
- TaxEval v2Not measured
- Tax Agent BenchVersion 126.63%± 3.1441 of 82
Vals AI, Tax Agent Bench, v1, 9 November 2026 · Source · Measured 9 November 2026 · Read 10 November 2026 · cost per task $0.13
- CorpFin v2Not measured
- Immigration BenchVersion 165.64%± 1.6417 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 JusticeVersion 172.86%± 0.7210 of 23
Vals AI, Access to Justice, v1, 10 November 2026 · Source · Measured 10 November 2026 · Read 10 November 2026 · cost per task $0.11
- Public Benefits BenchVersion 1.164.28%± 1.2523 of 50
Vals AI, Public Benefits Bench, v1.1, 12 October 2026 · Source · Measured 12 October 2026 · Read 10 November 2026 · cost per task $0.07
- Vals Legal IndexNot measured
- Vals IndexVersion 2.151.32%± 1.1327 of 50
Vals AI, Vals Index, v2.1, 18 October 2026 · Source · Measured 18 October 2026 · Read 10 November 2026 · cost per task $0.33
- GPQA Diamond (Vals-run)Not measured
- MMLU Pro (Vals-run)Not measured
- Artificial Analysis Intelligence IndexVersion 4.3.2 · Counts towards the PrudentScore
Artificial Analysis Intelligence Index v4.3.2: 39.5. 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), Tax Agent Bench, …) · 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
- 10 September 2026
- Status
- Generally available
- Context window
- 1M tokens
- Max output tokens
- 384K tokens
- List price
- $0.30 input · $1.20 outputper million tokens · Read 10 November 2026
- Weights
- Open
- = not yet recorded in the register.
05
Frequently asked questions about this model
Does DeepSeek V4.1 Flash pass the compliance gate for legal work?
No. No EU guarantee: Google Cloud Vertex AI: not in the EU or US column (global) 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 V4.1 Flash cost per task?
Vals computes $0.25 per completed task on the Legal Research Bench [1]. The list price is $0.30 per million input tokens and $1.20 per million output tokens.
How does DeepSeek V4.1 Flash score on legal research?
41.35 percent all-pass on the Vals AI Legal Research Bench, position 30 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
- GLM Legal
- Hy4
- DeepSeek V4.1 Flash 1017
- DeepSeek V4 Pro (0813)
- 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.