Gemini 3.8 Flash
Gemini 3.8 Flash is a model from Google. On the Vals AI Legal Research Bench it reaches 38.94 percent all-pass, position 38 of 91, within a standard error of ±3.39 percentage points at $1.63 per task, as at 9 November 2026 [1]. It passes the compliance gate and reaches a PrudentScore of 62 points.
- Generally available
- 2 September 2026
- PrudentScore
- 62out of 100position 6 of 30 with a score
- Compliance gate
- PassesGoogle Cloud Vertex AI: EU multi-region (ML processing in the EU) per Google's data-residency table (updated 2026-11-10); Google Cloud EMEA Limited (Dublin) is the contracting party for EMEA customers except France, Italy and Poland; Service Specific Terms §18 Training Restriction: "Google will not use Customer Data to train or fine-tune any AI/ML models without Customer's prior permission or instruction"
- Cost per task
- $1.63Vals AI, per completed task [1]
01
Compliance gate
Why
- Google Cloud Vertex AI: EU multi-region (ML processing in the EU) per Google's data-residency table (updated 2026-11-10); Google Cloud EMEA Limited (Dublin) is the contracting party for EMEA customers except France, Italy and Poland; Service Specific Terms §18 Training Restriction: "Google will not use Customer Data to train or fine-tune any AI/ML models without Customer's prior permission or instruction".
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 | EU multi-region (ML processing in the EU) | Yes | 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 PrudentScore38.94%± 3.3938 of 91
Vals AI, Legal Research Bench, v1, 9 November 2026 · Source · Measured 9 November 2026 · Read 10 November 2026 · cost per task $1.63
- Harvey LAB (Vals implementation)Version 1.112.08%± 2.5818 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 $3.66
- Harvey LAB (Vals implementation)Version 1 · Counts towards the PrudentScore10.00%± 2.4220 of 80
Vals AI, Harvey LAB (Vals implementation), v1, 18 October 2026 · Source · Measured 18 October 2026 · Read 10 November 2026 · cost per task $3.66
- LegalBench (Vals leaderboard)Version 186.99%± 0.438 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 274.45%± 0.8535 of 108
Vals AI, TaxEval v2, v2, 1 September 2026 · Source · Measured 1 September 2026 · Read 10 November 2026
- Tax Agent BenchVersion 132.12%± 3.3724 of 82
Vals AI, Tax Agent Bench, v1, 9 November 2026 · Source · Measured 9 November 2026 · Read 10 November 2026 · cost per task $0.86
- CorpFin v2Not measured
- Immigration BenchVersion 163.41%± 1.6121 of 26
Vals AI, Immigration Bench, v1, 9 November 2026 · Source · Measured 9 November 2026 · Read 10 November 2026 · cost per task $0.17
- Access to JusticeVersion 167.06%± 0.7621 of 23
Vals AI, Access to Justice, v1, 10 November 2026 · Source · Measured 10 November 2026 · Read 10 November 2026 · cost per task $0.32
- Public Benefits BenchVersion 1.165.29%± 1.2422 of 50
Vals AI, Public Benefits Bench, v1.1, 12 October 2026 · Source · Measured 12 October 2026 · Read 10 November 2026 · cost per task $1.01
- Vals Legal IndexVersion 169.78%± 1.7818 of 36
Vals AI, Vals Legal Index, v1, 9 November 2026 · Source · Measured 9 November 2026 · Read 10 November 2026 · cost per task $2.05
- Vals IndexVersion 2.255.95%± 1.1421 of 35
Vals AI, Vals Index, v2.2, 9 November 2026 · Source · Measured 9 November 2026 · Read 10 November 2026 · cost per task $5.03
- Vals IndexVersion 2.154.89%± 1.0218 of 50
Vals AI, Vals Index, v2.1, 18 October 2026 · Source · Measured 18 October 2026 · Read 10 November 2026 · cost per task $5.71
- GPQA Diamond (Vals-run)Version 194.44%± 1.484 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 190.22%± 0.295 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: 40.9. 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
- Model family
- Gemini
- Release date
- 2 September 2026
- Status
- Generally available
- Context window
- 1M tokens
- Max output tokens
- 66K tokens
- List price
- $0.75 input · $3.75 outputper million tokens · Read 10 November 2026
- Weights
- Closed
- = not yet recorded in the register.
05
Frequently asked questions about this model
Does Gemini 3.8 Flash pass the compliance gate for legal work?
Yes. Google Cloud Vertex AI: EU multi-region (ML processing in the EU) per Google's data-residency table (updated 2026-11-10); Google Cloud EMEA Limited (Dublin) is the contracting party for EMEA customers except France, Italy and Poland; Service Specific Terms §18 Training Restriction: "Google will not use Customer Data to train or fine-tune any AI/ML models without Customer's prior permission or instruction". Route: Google Cloud Vertex AI. The gate tests a route, not a model name; the sources are on this page.
What does Gemini 3.8 Flash cost per task?
Vals computes $1.63 per completed task on the Legal Research Bench [1]. The list price is $0.75 per million input tokens and $3.75 per million output tokens.
How does Gemini 3.8 Flash score on legal research?
38.94 percent all-pass on the Vals AI Legal Research Bench, position 38 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
- Claude Opus 4.862
- Claude Sonnet 5.562
- Gemini 4 Argon79
- Gemini 4 Carbon77
- Gemini 3.7 Flash58
- Gemini 3.5 Flash47
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.