Introducing Tenet, our first model post-trained for legal. Tenet is a Kimi K3 base that we post-trained with @FireworksAI_HQ on a corpus of publicly available legal data, synthetic data, and human expert data simulating long-horizon legal work. Training increases Tenet's all-pass rate by 82% on LAB and 22% on LAB Contracts relative to the Kimi K3 base model. It achieves state-of-the-art performance on LAB Contracts and places second on LAB. These gains generalize to other leading agentic benchmarks including @mercor's Apex Agents - Corporate Law, @crosbylegal's Redline Bench, and @scale_AI's Professional Reasoning Bench. Tenet is also optimized for token efficiency, operating at less than a fourth the cost of leading foundation models. We additionally post-trained three specialist models for Tenet to use as subagents: 1) M&A Diligence: post-trained with @baseten on our LAB Diligence environment in an RLM harness, this model is optimized for high-scale, long-horizon tasks. 2) Review Tables: trained with @appliedcompute on our Review Table environment, this model is state-of-the-art and cost-effective at high-volume document review and structured data extraction. 3) Firm Knowledge: trained with @EngramLab on our synthetic law firm environment, this model is optimized to learn and search over a firm's knowledge via memory and structured notes. More details on model training, environment design, benchmarking, results, and more in the article by @gabepereyra below. What's next for Harvey’s research? - Scaling LAB to more jurisdictions, practice areas and workflows - Scaling compute to bring new generalist models and capabilities to Harvey More to come soon.

More on Harvey Graph: harvey.ai/blog/improving-age…

A closer look at Harvey Graph. Starting with graphs for US Case Law and Spaces, Harvey Graph maps the connections between matters, documents, and legal knowledge so agents can start work with the context they need. In early Legal Agent Bench tests, adding a context graph raised rubric pass rates on firm-knowledge questions from 65% to 80%.

We built context graphs to help agents work through long-horizon legal tasks. Starting with Legal Agent Bench tasks in 11 categories like M&A diligence and contract negotiation, we had agents build context graphs of the underlying documents (without access to the eval tasks or grading rubrics). Context graphs dramatically improved agent performance on LAB tasks: - Firm Knowledge tasks: 65% → 80% - Precedent lists tasks: 67% → 80% - Matter counting tasks: 53% → 83% They also boost agent efficiency: we found a 48% cost reduction for agents given access to a context graph to assist their work. Full video below - more to come soon.

We trained NVIDIA Nemotron 3.5 Super VL on Harvey’s Legal Agent Bench. It now scores level with Opus 4.7 on rubric criteria, at $1.34 per million tokens vs $15. 🧵

Today, @harvey is partnering with Sourcery as our exclusive legal AI sponsor. Harvey has emerged as the dominant player in legal AI, with a $15.5B valuation & surpassing $400M in ARR. A couple months ago I sat down with Harvey Co-Founder & CEO @winstonweinberg, Co-Founder & President @gabepereyra, & Head of Applied Research @nikogrupen at the company’s San Francisco HQ to discuss frontier model research, proprietary legal intelligence, agentic workflows, & the economics of AI. Stats: › 3,500+ customers › 200K+ professionals › 80% of Am Law 100 firms › 5 of the Fortune 10 I am so excited to deepen our relationship with Harvey!

We're excited to help in-house teams build frontier legal organizations with Harvey. Our cofounder @gabepereyra shares our vision for bringing the business, in-house legal, and outside counsel together on one platform. Deep dive into the progress we've made building that platform across Intake, Contract Intelligence, Horizon Scanning, Shared Spaces, and Command Center:

Coming soon to Harvey: Gemini 4 Argon, Google’s newest frontier model. In early testing, Gemini 4 Argon excelled at analyzing agreements, filings, and diligence materials, with strong results in corporate M&A, antitrust and competition, and data privacy and cybersecurity.

When you build for the frontier ecosystem the frontier ecosystem responds! @harvey's Legal Agent Bench cited in @Meta's Muse Wonder launch, with models built specifically for professional agents. Strong scores from @ArtificialAnlys implementation of LAB scoring. Congrats @fikd @alexandr_wang & team

Today we are announcing Harvey LAB-AA v1.1 in collaboration with Harvey. This updates our scoring methodology for the Legal Agent Benchmark (LAB) to add a hallucination check and require correct responses to not include material misstatements. LAB-AA v1.1's new headline metric, Hallucination-Gated All-Pass Rate, only credits a task when the deliverables satisfy every rubric criterion and contain no material hallucinations. We define a material hallucination as one that would mislead a reader on a substantive point, such as a wrong contractually required date, while a minor hallucination is a real error that is unlikely to meaningfully affect the legal interpretation of a deliverable. Minor hallucinations are reported separately and do not affect the headline score. Grok 4.7 (xhigh) leads at 9.4% Hallucination-Gated All-Pass Rate, and >60% of otherwise passing results across the models tested at launch contain a material hallucination. This is the first step in enhancing the methodology for Harvey LAB-AA. In future updates, we’re working with Harvey to better account for the full set of factors lawyers value, including usability features like style and tone. Key takeaways: ➤ Top of the leaderboard: Grok 4.7 (xhigh) from @spacexai leads at 9.4% Hallucination-Gated All-Pass Rate, narrowly ahead of Muse Spark 1.3 (max) from @AIatMeta at 8.9% and GPT-6 Astra (max) from @OpenAI at 8.6% ➤ Hallucinations reshape the leaderboard: without the hallucination gate, Muse Spark 1.3 (max) would lead clearly with a 26.7% all-pass rate, but two thirds of those passes contain one or more material hallucinations, resulting in a Hallucination-Gated All-Pass Rate of 8.9%. GPT-6 Astra (max) retains almost all of its passes after the hallucination gate (8.9% to 8.6%) and moves from joint 10th to 3rd ➤ The GPT-6 model family is the most grounded: GPT-6 Astra (max) averages 0.03 material hallucinations per task (4 across all 120 tasks) and GPT-6 Sol (max) averages 0.07. When comparing six checker models on a 20-task subset, GPT-6 Astra had zero material hallucinations under every checker, including Claude Opus 5.5 (high). By comparison, Gemini 3.8 Flash (high) averages 13.96 material hallucinations per task. ➤ Top-scoring models aren’t the most expensive: Grok 4.7 (xhigh) takes the top spot on the leaderboard at a cost of ~$9.50 per task, under half the cost of Claude Fable 5.1 (max with fallback) at ~$21.70, the most expensive model. Muse Spark 1.3 (max) represents strong performance for its cost, landing in second for ~$4.20 per task Thank you to @nikogrupen and @ItsJulioPereyra from @harvey for their work on Harvey LAB and collaboration.

The return of wake-sleep. Wake-sleep algorithms were introduced by Hinton et al. in 1995 as a means of training neural networks by alternating two phases: a wake phase that learns from real data, and a sleep phase that learns from examples the network dreams up offline. We're starting to see them come back in a big way in agent-native products. As agents solve increasingly long-horizon, knowledge-intensive tasks, they'll need to learn from their own work, reviewing graded records of what they did offline and turning them into memory they carry into the next task. Sharing an overview of wake-sleep for legal agents and initial experimental results on Harvey LAB.