What AI Models Does Harvey Use?
In this article, we’ll cover the main models Harvey uses and how they compare.
Last updated: Nov 21, 2025
Overview
To help you maximize your impact, Harvey leverages different advanced AI Large Language Models (LLMs), each designed with unique strengths. When you ask Harvey for assistance, our multi-model system will break down the request into sub-tasks, select a model to use, then synthesize the outputs for you. The current models we use are a mix of the following:
- OpenAI GPT-5
- OpenAI o3 model suite
- OpenAI GPT-4.1 (4.1, 4.1-mini, 4.1-nano) and 4o model suite
- Google Gemini 2.5 Pro model suite
- Anthropic Sonnet/Opus 4 model suite
By default, Harvey’s 'Auto' mode will select for you, but if you prefer to choose yourself, workspace admins can enable Model Selector for individual users or across your workspace. Just keep in mind that there is no single model that’s best for every task so we recommend Auto.
Notes on the latest models:
- Gemini 3 Pro: We are working in parallel with the teams at Google and DeepMind to bring their Early Access model towards General Availability, at which point the model will be made available within Harvey.
- Claude Sonnet 4.5 and GPT-5.1 are available via selection in our Model Selector. The latter is only available for the US and EU. We’re currently testing these models to evaluate further integration.
- GPT-5 is included in Auto mode for Assistant chat and draft style tasks for US and EU customers. We will be expanding its integration in Auto mode as we continue testing the model for reliability at scale. If you prefer to use GPT-5 across product areas in your workspace now, it is available in the Model Selector for the US and EU.
Our Model Evaluation Process
Harvey’s model evaluation methodology is comprehensive so that we understand not only raw model performance, but also the safety and reliability of each model before including it in our system. The pillars of our model evaluation are BigLaw Bench, product performance, and unstructured evaluation.
After we evaluate a model, we revisit the evaluation throughout its lifecycle to ensure we’re offering our users the best functionality.
Model Comparison
To help you navigate the models we offer, we’ve put together a high-level comparison table. Use the horizontal scrollbar at the bottom of the table to view all columns, including availability by region.
Note: If model selector is enabled in your workspace but you’re not seeing a particular model, it may not be available for your region. Ask your Customer Success Manager to confirm what’s available to you.
Model | Developer | Model Release Date | Strengths | Weaknesses | BigLaw Bench Score | Knowledge Cut-off | Regional Availability |
|---|---|---|---|---|---|---|---|
GPT-5.1 | Open AI | November 12, 2025 |
|
| 91.8% | September 2024 |
|
GPT-5 (reasoning) | Open AI | August 7, 2025 |
|
| 89.22% | September 2024 |
|
o3 | Open AI | April 16, 2025 |
|
| 84.13% | June 2024 |
|
GPT-4.1 | Open AI | April 14, 2025 |
|
| 78.39% | June 2024 |
|
Gemini 2.5 Pro | March 25, 2025 |
|
| 85.02% | February 2025 |
| |
Claude Sonnet 4 | Anthropic | May 22, 2025 |
|
| 81.37% | January 2025 |
|
Opus 4 | Anthropic | May 22, 2025 |
|
| 82.70% | January 2025 |
|
Claude Sonnet 4.5 | Anthropic | September 29, 2025 |
|
| 89.55% | January 2025 |
|
Looking forward, the landscape of AI technology is continuously evolving, and so is Harvey. We are constantly evaluating the latest models and their performance to ensure we are always providing the most advanced and effective solutions. Stay up-to-date on model availability and feature enhancements by following our Release Notes.