Gemini 4 Carbon
Gemini 4 Carbon is a model from Google. On the Vals AI Legal Research Bench it reaches 55.77 percent all-pass, position 1 of 91, within a standard error of ±3.45 percentage points at $8.74 per task, as at 9 November 2026 [1]. It passes the compliance gate and reaches a PrudentScore of 77 points.
- Generally available
- 10 November 2026
- PrudentScore
- 77out of 100position 2 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
- $8.74Vals 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".
- Google logs prompts and responses for this model for up to 30 days for abuse monitoring (Google Frontier Model, Service Specific Terms §34), in the customer environment and without CMEK; accepted by Prudai (decision 10 November 2026).
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 PrudentScore55.77%± 3.451 of 91
Vals AI, Legal Research Bench, v1, 9 November 2026 · Source · Measured 9 November 2026 · Read 10 November 2026 · cost per task $8.74
- Harvey LAB (Vals implementation)Version 1.117.50%± 3.008 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 $6.52
- LegalBench (Vals leaderboard)Not measured
- CaseLaw v2Not measured
- TaxEval v2Not measured
- Tax Agent BenchVersion 151.78%± 3.601 of 82
Vals AI, Tax Agent Bench, v1, 9 November 2026 · Source · Measured 9 November 2026 · Read 10 November 2026 · cost per task $6.34
- CorpFin v2Not measured
- Immigration BenchNot measured
- Access to JusticeNot measured
- Public Benefits BenchNot measured
- Vals Legal IndexVersion 175.93%± 1.853 of 36
Vals AI, Vals Legal Index, v1, 9 November 2026 · Source · Measured 9 November 2026 · Read 10 November 2026 · cost per task $7.20
- Vals IndexVersion 2.270.45%± 0.973 of 35
Vals AI, Vals Index, v2.2, 9 November 2026 · Source · Measured 9 November 2026 · Read 10 November 2026 · cost per task $10.51
- GPQA Diamond (Vals-run)Not measured
- MMLU Pro (Vals-run)Not measured
- Artificial Analysis Intelligence IndexVersion 5.0
Artificial Analysis Artificial Analysis Intelligence Index v5.0: 59.4. Source: Artificial Analysis, Artificial Analysis Intelligence Index, v5.0, 29 October 2026, accessed 29 October 2026.
Artificial Analysis, Artificial Analysis Intelligence Index, v5.0, 29 October 2026 · Source · Measured 29 October 2026 · Read 29 October 2026
Source: Vals AI (Legal Research Bench, Harvey LAB (Vals implementation), Tax Agent Bench, Vals Legal Index, …) · 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
- 10 November 2026
- Status
- Generally available
- Context window
- 1M tokens
- Max output tokens
- 1M tokens
- List price
- $4.00 input · $20.00 outputper million tokens · Read 10 November 2026
- Weights
- Closed
- = not yet recorded in the register.
05
Frequently asked questions about this model
Does Gemini 4 Carbon 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". Google logs prompts and responses for this model for up to 30 days for abuse monitoring (Google Frontier Model, Service Specific Terms §34), in the customer environment and without CMEK; accepted by Prudai (decision 10 November 2026). Route: Google Cloud Vertex AI. The gate tests a route, not a model name; the sources are on this page.
What does Gemini 4 Carbon cost per task?
Vals computes $8.74 per completed task on the Legal Research Bench [1]. The list price is $4.00 per million input tokens and $20.00 per million output tokens.
How does Gemini 4 Carbon score on legal research?
55.77 percent all-pass on the Vals AI Legal Research Bench, position 1 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
- Gemini 4 Argon79
- Claude Opus 572
- Gemini 3.8 Flash62
- Gemini 3.7 Flash58
- Gemini 3.5 Flash47
- Gemini 3.6 Flash46
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.