Benchmark Almanac

MAUD

BigBird (MAUD fine-tuned) 57.8 tops its leaderboard
Not in model cards

Models classify provisions in merger agreements into expert-defined legal categories. The benchmark compares predictions with lawyer annotations and reports precision-recall area and micro and macro F1.

The dataset contains more than 39,000 examples and 47,000 annotations. Training examples are separate from the held-out evaluation.

Released
January 2023
Kind
Law
Level
Expert
Scored
Checked automatically
Answers
Multiple choice
Tasks
All public
Measures
Capability
Subject
Law
Language
English
In and out
Text → Text
Interaction
Single turn
Refresh
One fixed set
Run by
Anyone
In views
Law and finance

In the authors’ words

Reading comprehension of legal text can be a particularly challenging task due to the length and complexity of legal clauses and a shortage of expert-annotated datasets. To address this challenge, we introduce the Merger Agreement Understanding Dataset (MAUD), an expert-annotated reading comprehension dataset based on the American Bar Association's 2021 Public Target Deal Points Study, with over 39,000 examples and over 47,000 total annotations. Our fine-tuned Transformer baselines show promising results, with models performing well above random on most questions. However, on a large subset of questions, there is still room for significant improvement. As the only expert-annotated merger agreement dataset, MAUD is valuable as a benchmark for both the legal profession and the NLP community.

Abstract of MAUD: An Expert-Annotated Legal NLP Dataset for Merger Agreement Understanding (arXiv:2301.00876, CC0)
5
Entries in its paper, 0 models we track

BigBird (MAUD fine-tuned) tops the leaderboard with 57.8

Best score per entry from the benchmark's paper, read on November 19th, 2026. A paper’s table doesn’t add newer models. Where a model ran with several settings or harnesses, we keep its best. Names in gray aren't in our model list: fine-tunes, agent systems, products and older models. They don't count toward leaders.

  1. 1 BigBird (MAUD fine-tuned) single-task 57.8
  2. 2 DeBERTa (MAUD fine-tuned) single-task 57.1
  3. 3 LegalBERT (MAUD fine-tuned) single-task 55.9
  4. 4 RoBERTa (MAUD fine-tuned) single-task 55.5
  5. 5 BERT (MAUD fine-tuned) single-task 52.6

Source: The MAUD paper

#EntryScoreSettingDateSource
1 BigBird (MAUD fine-tuned) 57.8 single-task Official leaderboard
2 DeBERTa (MAUD fine-tuned) 57.1 single-task Official leaderboard
3 LegalBERT (MAUD fine-tuned) 55.9 single-task Official leaderboard
4 RoBERTa (MAUD fine-tuned) 55.5 single-task Official leaderboard
5 BERT (MAUD fine-tuned) 52.6 single-task Official leaderboard

No lab model card reports it yet

We read the headline results of 540 launch posts from 57 labs, and none of them list this benchmark.

More in Law, finance and medicine

All 637 in Law, finance and medicine
  • MedXpertQA-MM In use Models answer expert-level medical exam questions that combine images with clinical records and test results. Scoring is accuracy. Qwen 3.8 Max 80.4%
  • HealthBench Professional In use 525 physician-authored tasks from real clinician chats (care consult, documentation, research) with physician-adjudicated rubrics. Claude Sonnet 5.5 69.2%
  • HealthBench In use 5,000 realistic health conversations graded against physician-written rubrics. A length-adjusted variant penalizes verbosity. GPT-5 67.2%
  • FinSearchComp In use Agents search the web to fetch live financial data, look up history, and run multi-step investigations, across 635 expert-written questions. Scored by answer accuracy. Ling-3.1-flash 81.7%
  • KorMedMCQA In use Models answer 7,469 multiple-choice questions from Korean licensing exams for doctors, nurses, pharmacists and dentists, held from 2012 to 2024. o1-preview 92.7%
  • Harvey LAB-AA v1.1 In use Artificial Analysis's run of Harvey's Legal Agent Benchmark on Harvey's newer private set of 120 tasks across 24 practice areas. A deliverable with a material hallucination scores zero, and the headline is the share of judges who find every rubric criterion passed. GPT-6.2 Astra 15%

Data audit

All 8 checks pass. Every benchmark

Catalog record 2 pass
  • Pass Task access All tasks are public.
  • Pass Confidence Checked against a primary source.
Scores 2 pass 3 notes
  • Pass Independent runs Scores from the benchmark’s paper (5 entries).
  • Pass Models scored 5 entries on its leaderboard, none a model we track.
  • Note Newest score No scores yet.
  • Note Frontier models No models scored yet.
  • Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
  • Pass Importer We read the board on arxiv.org: 5 entries at the last read, none a model we track.
  • Pass Last read November 19th, 2026.
  • Pass Read worked The last read worked.
Consistency 1 pass 1 note
  • Note Lab claims No model has both a lab number and an independent run.
  • Pass Known issues No published audit found problems.

How we check