Trending Now
Commercial

Which AI Model Is Best for Legal Work? What 2026 Research Says About Accuracy

September 24, 2026

Which AI Model Is Best for Legal Work? What 2026 Research Says About Accuracy

Law firms, funders and legal departments are being sold AI for contract review, legal research and citation checking, and the models change every few months. So we looked only at independent studies published in 2026 that tested the current generation of models from OpenAI, Anthropic and Google on real legal tasks. The short version: the best models are now genuinely good at reading and extracting from documents you give them, still unreliable at recalling law from memory, and the commercial legal research tools lag behind the best custom systems.

At a Glance

Best overall model for legal document work: Google's Gemini 3.1 Pro. It was at or near the top in every 2026 study that tested it, and it was usually the fastest and cheapest of the leaders. OpenAI's GPT-5.5 found slightly more errors in contract review, and Anthropic's Claude models were the most careful about not flagging problems that weren't there.

Best accuracy recorded on a full legal task: 92%, on a 50-state statutory research test run by Stanford, achieved by a purpose-built research tool. The lesson is that how the AI is set up matters as much as which model sits underneath it.

Range of accuracy: from under 7% (asking a model to recall exact case citations from memory) to 99–100% (catching a citation to the wrong case when the model can read the source). Most real-world document tasks landed between 60% and 85%.

Westlaw and Lexis AI: 58% and 64% accuracy on a Stanford statutory survey test, below a custom-built tool at 83–92%.

Biggest single improvement: giving the model the actual documents instead of asking it from memory cut fabricated citations from roughly 15–40% to about 4–15%, and to under 0.2% with a well-built retrieval system.

Key Takeaways

The model to use. For contract review and extraction, start with Gemini 3.1 Pro. It matched the top performer on catching contract errors (74% vs. 75%) at about one-seventh of the cost and in 90 seconds instead of nine minutes. If catching every possible issue matters more than time or cost, GPT-5.5 with reasoning turned on found the most. For checking citations in a brief, the best 2026 results came from GPT-5 running as an agent and from Claude Code with Claude Opus, which was the most precise.

How to Use It

  • Give it the documents. Never ask a model to supply case law or citations from memory.
  • Turn on the model's "reasoning" or "thinking" mode for review work. It improved error-catching by 9 to 11 points in contract review.
  • Use it as a first pass and a second reviewer, not the final reviewer.
  • For research, use a tool that pulls from a full, current database of the law, because weak retrieval, not the model, causes many of the errors.

What to Expect

  • Contract extraction (pulling out dates, parties, termination and liability terms): about 80–84% accuracy for the best models.
  • Final contract proofreading (defined terms, cross-references, inconsistent language): the best models catch about three-quarters of errors. On a 60-page agreement, expect it to miss some.
  • Citation checking: nearly all citations to the wrong case get caught, but wrong pinpoint pages slip through 20% to 60% of the time.
  • Research answers grounded in the right documents: roughly 6–11% of answers still contain an unsupported statement.

What to Look Out For

  • Citations from memory. When asked to recall exact citations without sources, even the best model scored under 7 out of 100, and 20 of 21 models gave confident, wrong answers more than 94% of the time.
  • Right case, wrong page. Models tend to approve a citation because the case is on the right topic, even when the cited page doesn't support the point.
  • Questions with a false premise. If your question assumes something that isn't true, models often go along with it.
  • Legal research tools' marketing. Westlaw AI and Lexis+ AI trailed a custom-built tool by 19 to 25 points on a Stanford test.
  • Studies funded by vendors. Some of the best-looking results come from companies selling legal AI. Check who ran the test.

Best Practices

  • Ground every task in source documents, and require the model to quote the passage it relied on.
  • Check every citation yourself at the pinpoint page before filing. Automated checkers help but don't replace this.
  • Turn on reasoning mode for review tasks and accept that it's slower.
  • Test a model on a few of your own documents before rolling it out. Rankings change by task.
  • Re-test when a new model version arrives; this field moves in months, not years.
  • Keep a human reviewer accountable for anything that goes to a court, a client or a counterparty.

What the Studies Found

Contract proofreading. In August 2026, researchers had experienced lawyers plant errors in contracts (misused defined terms, wrong cross-references, wrong party names, contradictions) and tested ten current models on catching them. GPT-5.5 caught 75% of errors, Gemini 3.1 Pro 74%, Claude Sonnet 4.6 69% and Claude Opus 4.7 62%. GPT-5.5 cost $1.38 per contract and took about nine minutes; Gemini 3.1 Pro cost $0.19 and took about 90 seconds. Turning on reasoning mode added 9 to 11 points. Every model was far cheaper than a lawyer, and none was close to perfect.

Contract extraction. A May 2026 study tested models on pulling 26 standard fields out of contracts. Among the major models, Gemini 3.1 Pro scored highest (82%), with Claude Opus 4.6 (82%) and Claude Sonnet 4.6 (80%) close behind and GPT-5.4 at 78%. A smaller legal-specific model built by the study's authors scored 84% at far lower cost. The authors work for Onit, which makes that model.

Made-up citations and facts. A January 2026 study had expert reviewers check 2,700 legal answers from 12 models. Asked without source documents, the best models (GPT-5.2 and Gemini 3.0 Pro) cited something false about 15–17% of the time, and the worst over 30%. Giving the models the relevant documents cut that to about 4–15%. A more carefully built retrieval system brought it below 0.2% for every model.

Research with sources. A March 2026 study found that when models answer from retrieved legal texts, Gemini 3.1 Pro produced unsupported statements 5.7% of the time versus 11.3% for GPT-5.2, and that the quality of the search step mattered more than the choice of model. Its authors sell the search component that performed best. An August 2026 study of eight research setups found unsupported answers ranging from under 10% for the best to nearly half for the worst, with the worst results on questions built on a false assumption.

Westlaw and Lexis. In a February 2026 Stanford study, researchers tested legal AI tools against a Department of Labor survey of state unemployment insurance laws. Westlaw AI scored 58% and Lexis+ AI 64%, while a custom statutory research tool scored 83%, rising to 92% after the researchers found that some of its "errors" were gaps in the government's own survey.

Citation checking. A June 2026 study found more than 1,000 court filings containing fabricated citations, a number growing every year, and tested AI checkers on catching them. GPT-5, working as an agent that looks up cases, caught 83% of planted errors; Claude Code running Claude Opus 4.8 was the most precise and scored best overall. No model reliably caught wrong pinpoint cites, partly because page numbers often sit behind Westlaw and Lexis paywalls. A separate August 2026 study found models catch 93–100% of citations to the wrong case but miss many citations to the wrong page, and even GPT-5.4 with full reasoning missed 40% of wrong pinpoints in court opinions.

Citations from memory. A May 2026 study built from 1,000 real U.S. judicial opinions asked 21 models to recall exact case citations without any sources. The best, Claude Sonnet 4.5, scored under 7 out of 100.

The Bottom Line

The 2026 research is consistent: today's best models, led by Gemini 3.1 Pro, GPT-5.5 and Claude, are useful and cheap for first-pass contract review and extraction when they work from the documents in front of them. They still invent law when asked from memory and still miss wrong pinpoint citations, so a lawyer has to verify anything that leaves the building.

Sources (All 2026)

  • Bang et al., "ContractScrub: A benchmark for final review of legal contracts" (Aug. 2026), arXiv:2608.20204
  • Lincoln et al., "A Few Good Clauses: Comparing LLMs vs Domain-Trained Small Language Models on Structured Contract Extraction" (May 2026), arXiv:2605.05532
  • Dantart, "Reliability by design: quantifying and eliminating fabrication risk in LLMs" (Jan. 2026), arXiv:2601.15476
  • Butler and Butler, "Legal RAG Bench: an end-to-end benchmark for legal RAG" (Mar. 2026), arXiv:2603.01710
  • Das et al., "How Much Do Legal RAG Systems Still Hallucinate?" (Aug. 2026), arXiv:2608.14210
  • Afane et al., "Benchmarking Legal RAG: The Promise and Limits of AI Statutory Surveys" (Feb. 2026), arXiv:2603.03300
  • Liu, Stammbach and Henderson, "Who Checks the Citations? Benchmarking Legal Hallucination Detection" (June 2026), arXiv:2606.21155
  • Verma, "Is this Citation on Point?" (Aug. 2026), arXiv:2608.12571
  • Chen et al., "LegalCiteBench: Evaluating Citation Reliability in Legal Language Models" (May 2026), arXiv:2605.10186

Commercial

View All
Commercial

Deminor’s Wouter de Jong Sees Untapped Dutch Demand for Commercial and Patent Dispute Funding

Deminor's newest Dutch hire has said many sound business-to-business disputes in the Netherlands go unpursued because of cost, risk or resource constraints, pointing to an opening for litigation funders.

As reported by Litigation Finance Insider, Wouter de Jong discussed his move into funding in an interview published on 4 October. De Jong joined Deminor as Senior Legal Counsel in its Utrecht office after more than 14 years in disputes, including eight as a patent litigator in private practice and six as Head of Litigation at a major international company, as Deminor announced in September.

He said litigation funding is less unfamiliar to Dutch companies than it was 15 years ago but remains poorly understood. Two misconceptions recur with clients: the non-recourse "no cure, no pay" structure, and the extent to which Deminor offers litigation expertise beyond capital. He credited the Netherlands' legal system, efficient proceedings and strong judiciary for producing meaningful outcomes within reasonable timeframes.

De Jong also highlighted intellectual property. The Unified Patent Court, he said, lets patentees resolve disputes across larger territories in a single forum, and he has seen rising local inquiries about patent funding. Patent cases demand deeper underwriting of the technology and the scope of protection, making them slower to assess than typical commercial disputes.

The interview signals where Deminor expects growth from its Dutch presence, which opened in June as its tenth office worldwide: single-claim commercial and IP disputes, rather than the collective actions for which the Dutch market is better known.

Commercial

Loopa Finance’s Gouveia Urges Litigation Funding Rules That Protect Transparency Without Capping Returns

A senior investment manager at Loopa Finance has argued that litigation finance regulation should safeguard transparency and independence without restricting pricing, access to capital or the industry's ability to innovate.

As reported by Litigation Finance Insider, Marina Gouveia, Senior Investment Manager at Loopa Finance, said in a commentary published on 4 October that standards-based oversight is preferable to prescriptive statutory rules. She identified transparency, independence, contractual clarity and the integrity of proceedings as the priorities.

Gouveia noted that the market spans single-case funding, portfolio financing, award monetisation and law firm or corporate structures, and that sophisticated corporate clients and individual consumers have very different needs. A uniform regime, she suggested, would fit neither well. She also warned that return caps could make some claims less commercially attractive to finance, particularly those needing large upfront costs or long proceedings, which could narrow access to justice.

She accepted that some regulatory goals are legitimate, including managing conflicts of interest, ensuring parties understand their agreements, verifying that funders have the resources to perform, and protecting claimants' control over strategy and settlement. Her preferred route is standards that evolve through courts, arbitral institutions, counsel and funders as new risks emerge, rather than legislation attempting to anticipate future products.

The piece names no specific jurisdictions or bills. It arrives as regulators in the UK, EU and several US states continue to debate disclosure and oversight rules, and it reflects the self-regulation approach funders such as Loopa have promoted through bodies including the European Litigation Funders Association.

Commercial

PGMBM Opposes Bid to Hold 400,000-Claimant Mariana Hearing in Private

Pogust Goodhead, trading as PGMBM, has said it is opposing an application to hold today's High Court hearing on who represents more than 400,000 claimants in the Mariana Dam litigation under seal.

According to a statement issued by PGMBM, lawyers acting for the Mariana Client Committee served an application on Monday asking the court to hold the hearing in private. A PGMBM spokesperson said the firm believes the move "flies in the face of access to justice" for the claimants affected by the disaster, and described transparency for clients as fundamental. PGMBM said it is urgently asking the judge to reject the application in the public interest.

The hearing is an expedited two-day session on 5 and 6 October to decide which firm should act for the claimants. As Legal Futures reported, the High Court earlier refused a request to stay the proceedings and directed that the representation dispute be determined at that hearing, rejecting calls for it to be held in private. The dispute pits PGMBM against Bailey Glasser International, which the Client Committee has sought to instruct in its place.

The statement did not say how the court has responded to the new application, and the application itself was supplied to media only as an attachment. PGMBM's account is one side of a contested matter, and the Client Committee's lawyers have not been quoted.

The fight over the case, a claim against BHP over the 2015 Fundão dam collapse, has drawn attention across the litigation funding market because control of a mass claim of this size determines how funders, lawyers and claimants are aligned ahead of the quantum trial listed for April 2027.