Mistral AI
Mistral Medium 3.5
Mistral Medium 3.5 is a model with open weights from Mistral AI. On the Vals AI Legal Research Bench it reaches 9.13 percent all-pass, position 83 of 91, within a standard error of ±2.00 percentage points at $1.31 per task, as at 9 November 2026 [1]. It passes the compliance gate and reaches a PrudentScore of 23 points.
- Retired
- Open weights
- 29 April 2026
- PrudentScore
- 23out of 100position 29 of 30 with a score
- Compliance gate
- PassesMicrosoft Azure Foundry: Data Zone Standard Europe, version 1, EU regions: francecentral, germanywestcentral, italynorth, polandcentral, spaincentral, swedencentral, westeurope in Microsoft's Europe table (updated 2026-10-19); Contracting party Microsoft Ireland Operations Limited; Microsoft: prompts and completions "are NOT used to train any generative AI foundation models without your permission or instruction"
- Cost per task
- $1.31Vals AI, per completed task [1]
01
Compliance gate
Why
- Microsoft Azure Foundry: Data Zone Standard Europe, version 1, EU regions: francecentral, germanywestcentral, italynorth, polandcentral, spaincentral, swedencentral, westeurope in Microsoft's Europe table (updated 2026-10-19); Contracting party Microsoft Ireland Operations Limited; Microsoft: prompts and completions "are NOT used to train any generative AI foundation models without your permission or instruction".
- Mistral marks this model as Deprecated on docs.mistral.ai (deprecation date 10/31/2026, replacement Mistral Large 4); Azure Foundry still lists it in the Data Zone Europe table.
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 |
|---|---|---|---|
| Microsoft Azure (Foundry Models) | Data Zone Standard Europe, version 1, EU regions: francecentral, germanywestcentral, italynorth, polandcentral, spaincentral, swedencentral, westeurope | 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 PrudentScore9.13%± 2.0083 of 91
Vals AI, Legal Research Bench, v1, 9 November 2026 · Source · Measured 9 November 2026 · Read 10 November 2026 · cost per task $1.31
- Harvey LAB (Vals implementation)Version 1 · Counts towards the PrudentScore0.42%± 0.0062 of 80
Vals AI, Harvey LAB (Vals implementation), v1, 18 October 2026 · Source · Measured 18 October 2026 · Read 10 November 2026 · cost per task $6.07
- LegalBench (Vals leaderboard)Not measured
- CaseLaw v2Version 244.16%± 1.0653 of 54
Vals AI, CaseLaw v2, v2, 4 May 2026 · Source · Measured 4 May 2026 · Read 10 November 2026
- TaxEval v2Version 267.99%± 0.9288 of 108
Vals AI, TaxEval v2, v2, 1 September 2026 · Source · Measured 1 September 2026 · Read 10 November 2026
- Tax Agent BenchVersion 14.48%± 1.4779 of 82
Vals AI, Tax Agent Bench, v1, 9 November 2026 · Source · Measured 9 November 2026 · Read 10 November 2026 · cost per task $1.44
- CorpFin v2Version 258.78%± 0.9779 of 108
Vals AI, CorpFin v2, v2, 12 August 2026 · Source · Measured 12 August 2026 · Read 10 November 2026
- Immigration BenchNot measured
- Access to JusticeNot measured
- Public Benefits BenchNot measured
- Vals Legal IndexNot measured
- Vals IndexNot measured
- GPQA Diamond (Vals-run)Version 134.85%± 2.39108 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 175.33%± 0.4297 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: 14.2. 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), CaseLaw v2, 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
- Mistral AI
- Model family
- Mistral
- Release date
- 29 April 2026
- Status
- Retired
- Context window
- 262K tokens
- Max output tokens
- 80K tokens
- List price
- $1.50 input · $7.50 outputper million tokens · Read 10 November 2026
- Weights
- Open
- = not yet recorded in the register.
05
Frequently asked questions about this model
Does Mistral Medium 3.5 pass the compliance gate for legal work?
Yes. Microsoft Azure Foundry: Data Zone Standard Europe, version 1, EU regions: francecentral, germanywestcentral, italynorth, polandcentral, spaincentral, swedencentral, westeurope in Microsoft's Europe table (updated 2026-10-19); Contracting party Microsoft Ireland Operations Limited; Microsoft: prompts and completions "are NOT used to train any generative AI foundation models without your permission or instruction". Mistral marks this model as Deprecated on docs.mistral.ai (deprecation date 10/31/2026, replacement Mistral Large 4); Azure Foundry still lists it in the Data Zone Europe table. Route: Microsoft Azure (Foundry Models). The gate tests a route, not a model name; the sources are on this page.
What does Mistral Medium 3.5 cost per task?
Vals computes $1.31 per completed task on the Legal Research Bench [1]. The list price is $1.50 per million input tokens and $7.50 per million output tokens.
How does Mistral Medium 3.5 score on legal research?
9.13 percent all-pass on the Vals AI Legal Research Bench, position 83 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
- GPT 5.4 Mini25
- GPT 5.4 (xhigh)0
- Mistral Large 4 (GA, 26.10)
- Mistral Large 4 (preview)
- Devstral 2
- Magistral Medium 1.2 (09/2025)
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.